{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.991383679675621, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0040547389761784085, "grad_norm": 6.520535209179236, "learning_rate": 3.2520325203252037e-07, "loss": 0.8354, "step": 1 }, { "epoch": 0.008109477952356817, "grad_norm": 6.210635974632585, "learning_rate": 6.504065040650407e-07, "loss": 0.8068, "step": 2 }, { "epoch": 0.012164216928535226, "grad_norm": 6.41624418658374, "learning_rate": 9.75609756097561e-07, "loss": 0.8156, "step": 3 }, { "epoch": 0.016218955904713634, "grad_norm": 6.183669782384739, "learning_rate": 1.3008130081300815e-06, "loss": 0.8123, "step": 4 }, { "epoch": 0.02027369488089204, "grad_norm": 6.095983868856339, "learning_rate": 1.6260162601626018e-06, "loss": 0.8397, "step": 5 }, { "epoch": 0.024328433857070453, "grad_norm": 5.575457640368753, "learning_rate": 1.951219512195122e-06, "loss": 0.7889, "step": 6 }, { "epoch": 0.02838317283324886, "grad_norm": 4.235187291101561, "learning_rate": 2.2764227642276426e-06, "loss": 0.7544, "step": 7 }, { "epoch": 0.03243791180942727, "grad_norm": 4.163980470033908, "learning_rate": 2.601626016260163e-06, "loss": 0.768, "step": 8 }, { "epoch": 0.03649265078560568, "grad_norm": 2.25777357705032, "learning_rate": 2.926829268292683e-06, "loss": 0.7156, "step": 9 }, { "epoch": 0.04054738976178408, "grad_norm": 2.058420021748684, "learning_rate": 3.2520325203252037e-06, "loss": 0.7275, "step": 10 }, { "epoch": 0.044602128737962494, "grad_norm": 2.010294801637343, "learning_rate": 3.577235772357724e-06, "loss": 0.7081, "step": 11 }, { "epoch": 0.048656867714140906, "grad_norm": 3.8307386974818822, "learning_rate": 3.902439024390244e-06, "loss": 0.7164, "step": 12 }, { "epoch": 0.05271160669031931, "grad_norm": 4.237507185958049, "learning_rate": 4.227642276422765e-06, "loss": 0.7398, "step": 13 }, { "epoch": 0.05676634566649772, "grad_norm": 4.2039151890608215, "learning_rate": 4.552845528455285e-06, "loss": 0.7034, "step": 14 }, { "epoch": 0.060821084642676125, "grad_norm": 3.949662931094457, "learning_rate": 4.8780487804878055e-06, "loss": 0.6932, "step": 15 }, { "epoch": 0.06487582361885454, "grad_norm": 3.4614624279855075, "learning_rate": 5.203252032520326e-06, "loss": 0.6894, "step": 16 }, { "epoch": 0.06893056259503294, "grad_norm": 3.086094145208543, "learning_rate": 5.528455284552846e-06, "loss": 0.6593, "step": 17 }, { "epoch": 0.07298530157121136, "grad_norm": 2.32213661076122, "learning_rate": 5.853658536585366e-06, "loss": 0.6369, "step": 18 }, { "epoch": 0.07704004054738976, "grad_norm": 1.5668431550155164, "learning_rate": 6.178861788617887e-06, "loss": 0.6506, "step": 19 }, { "epoch": 0.08109477952356817, "grad_norm": 1.234190423790071, "learning_rate": 6.504065040650407e-06, "loss": 0.6114, "step": 20 }, { "epoch": 0.08514951849974658, "grad_norm": 1.4219320760674263, "learning_rate": 6.829268292682928e-06, "loss": 0.6308, "step": 21 }, { "epoch": 0.08920425747592499, "grad_norm": 1.5541197397308069, "learning_rate": 7.154471544715448e-06, "loss": 0.6209, "step": 22 }, { "epoch": 0.0932589964521034, "grad_norm": 1.1365139390619783, "learning_rate": 7.4796747967479676e-06, "loss": 0.5988, "step": 23 }, { "epoch": 0.09731373542828181, "grad_norm": 0.8513555095701546, "learning_rate": 7.804878048780489e-06, "loss": 0.5892, "step": 24 }, { "epoch": 0.10136847440446022, "grad_norm": 0.8873270984233783, "learning_rate": 8.130081300813009e-06, "loss": 0.5882, "step": 25 }, { "epoch": 0.10542321338063862, "grad_norm": 0.8972987625999073, "learning_rate": 8.45528455284553e-06, "loss": 0.571, "step": 26 }, { "epoch": 0.10947795235681702, "grad_norm": 0.7579768926425573, "learning_rate": 8.78048780487805e-06, "loss": 0.5823, "step": 27 }, { "epoch": 0.11353269133299544, "grad_norm": 0.77937986912765, "learning_rate": 9.10569105691057e-06, "loss": 0.5703, "step": 28 }, { "epoch": 0.11758743030917385, "grad_norm": 0.8624931891060162, "learning_rate": 9.43089430894309e-06, "loss": 0.5715, "step": 29 }, { "epoch": 0.12164216928535225, "grad_norm": 0.7264783922704449, "learning_rate": 9.756097560975611e-06, "loss": 0.5707, "step": 30 }, { "epoch": 0.12569690826153065, "grad_norm": 0.5808634888264488, "learning_rate": 1.008130081300813e-05, "loss": 0.5488, "step": 31 }, { "epoch": 0.12975164723770907, "grad_norm": 0.830773882469516, "learning_rate": 1.0406504065040652e-05, "loss": 0.5426, "step": 32 }, { "epoch": 0.1338063862138875, "grad_norm": 0.7553003145635514, "learning_rate": 1.0731707317073172e-05, "loss": 0.5429, "step": 33 }, { "epoch": 0.13786112519006588, "grad_norm": 0.47972307618395127, "learning_rate": 1.1056910569105692e-05, "loss": 0.5559, "step": 34 }, { "epoch": 0.1419158641662443, "grad_norm": 0.6058342951838358, "learning_rate": 1.1382113821138213e-05, "loss": 0.5277, "step": 35 }, { "epoch": 0.14597060314242272, "grad_norm": 0.5608054179839462, "learning_rate": 1.1707317073170731e-05, "loss": 0.5343, "step": 36 }, { "epoch": 0.1500253421186011, "grad_norm": 0.5701090655087153, "learning_rate": 1.2032520325203254e-05, "loss": 0.5416, "step": 37 }, { "epoch": 0.15408008109477953, "grad_norm": 0.5290214901886344, "learning_rate": 1.2357723577235774e-05, "loss": 0.5212, "step": 38 }, { "epoch": 0.15813482007095794, "grad_norm": 0.5254512454783207, "learning_rate": 1.2682926829268294e-05, "loss": 0.5295, "step": 39 }, { "epoch": 0.16218955904713633, "grad_norm": 0.46094930420962243, "learning_rate": 1.3008130081300815e-05, "loss": 0.5196, "step": 40 }, { "epoch": 0.16624429802331475, "grad_norm": 0.5162228941731029, "learning_rate": 1.3333333333333333e-05, "loss": 0.5157, "step": 41 }, { "epoch": 0.17029903699949317, "grad_norm": 0.49100293738362333, "learning_rate": 1.3658536585365855e-05, "loss": 0.5284, "step": 42 }, { "epoch": 0.17435377597567156, "grad_norm": 0.3846334912259837, "learning_rate": 1.3983739837398376e-05, "loss": 0.5251, "step": 43 }, { "epoch": 0.17840851495184998, "grad_norm": 0.4873835342219269, "learning_rate": 1.4308943089430896e-05, "loss": 0.5221, "step": 44 }, { "epoch": 0.1824632539280284, "grad_norm": 0.4241888059979549, "learning_rate": 1.4634146341463415e-05, "loss": 0.5104, "step": 45 }, { "epoch": 0.1865179929042068, "grad_norm": 0.40506258341022583, "learning_rate": 1.4959349593495935e-05, "loss": 0.5057, "step": 46 }, { "epoch": 0.1905727318803852, "grad_norm": 0.416761505727498, "learning_rate": 1.528455284552846e-05, "loss": 0.5119, "step": 47 }, { "epoch": 0.19462747085656362, "grad_norm": 0.433533402417942, "learning_rate": 1.5609756097560978e-05, "loss": 0.5029, "step": 48 }, { "epoch": 0.198682209832742, "grad_norm": 0.4572766009052568, "learning_rate": 1.5934959349593496e-05, "loss": 0.5018, "step": 49 }, { "epoch": 0.20273694880892043, "grad_norm": 0.4477029779994196, "learning_rate": 1.6260162601626018e-05, "loss": 0.5013, "step": 50 }, { "epoch": 0.20679168778509882, "grad_norm": 0.3830938693428912, "learning_rate": 1.6585365853658537e-05, "loss": 0.5137, "step": 51 }, { "epoch": 0.21084642676127724, "grad_norm": 0.41722225266819757, "learning_rate": 1.691056910569106e-05, "loss": 0.4997, "step": 52 }, { "epoch": 0.21490116573745566, "grad_norm": 0.4951626049087007, "learning_rate": 1.7235772357723578e-05, "loss": 0.4988, "step": 53 }, { "epoch": 0.21895590471363405, "grad_norm": 0.38588438724583163, "learning_rate": 1.75609756097561e-05, "loss": 0.498, "step": 54 }, { "epoch": 0.22301064368981247, "grad_norm": 0.5537622023501061, "learning_rate": 1.788617886178862e-05, "loss": 0.5001, "step": 55 }, { "epoch": 0.22706538266599088, "grad_norm": 0.6286318881031782, "learning_rate": 1.821138211382114e-05, "loss": 0.4934, "step": 56 }, { "epoch": 0.23112012164216927, "grad_norm": 0.4440526326424466, "learning_rate": 1.8536585365853663e-05, "loss": 0.4968, "step": 57 }, { "epoch": 0.2351748606183477, "grad_norm": 0.6117133621866535, "learning_rate": 1.886178861788618e-05, "loss": 0.4993, "step": 58 }, { "epoch": 0.2392295995945261, "grad_norm": 0.509078554787161, "learning_rate": 1.91869918699187e-05, "loss": 0.4915, "step": 59 }, { "epoch": 0.2432843385707045, "grad_norm": 0.5375677633576676, "learning_rate": 1.9512195121951222e-05, "loss": 0.4911, "step": 60 }, { "epoch": 0.24733907754688292, "grad_norm": 0.7144947215416104, "learning_rate": 1.983739837398374e-05, "loss": 0.4976, "step": 61 }, { "epoch": 0.2513938165230613, "grad_norm": 0.8553806809531243, "learning_rate": 2.016260162601626e-05, "loss": 0.5175, "step": 62 }, { "epoch": 0.2554485554992397, "grad_norm": 1.0375992750767526, "learning_rate": 2.048780487804878e-05, "loss": 0.5037, "step": 63 }, { "epoch": 0.25950329447541814, "grad_norm": 0.6408226541563796, "learning_rate": 2.0813008130081303e-05, "loss": 0.4766, "step": 64 }, { "epoch": 0.26355803345159656, "grad_norm": 0.7069146172091172, "learning_rate": 2.1138211382113822e-05, "loss": 0.4843, "step": 65 }, { "epoch": 0.267612772427775, "grad_norm": 0.7853197858504265, "learning_rate": 2.1463414634146344e-05, "loss": 0.4788, "step": 66 }, { "epoch": 0.27166751140395334, "grad_norm": 0.8848595345120048, "learning_rate": 2.1788617886178863e-05, "loss": 0.5097, "step": 67 }, { "epoch": 0.27572225038013176, "grad_norm": 0.7813699328938516, "learning_rate": 2.2113821138211385e-05, "loss": 0.4981, "step": 68 }, { "epoch": 0.2797769893563102, "grad_norm": 0.8666150984131747, "learning_rate": 2.2439024390243907e-05, "loss": 0.4995, "step": 69 }, { "epoch": 0.2838317283324886, "grad_norm": 0.7310582321891815, "learning_rate": 2.2764227642276426e-05, "loss": 0.4929, "step": 70 }, { "epoch": 0.287886467308667, "grad_norm": 0.745035757507799, "learning_rate": 2.3089430894308948e-05, "loss": 0.4925, "step": 71 }, { "epoch": 0.29194120628484543, "grad_norm": 0.7202896923895654, "learning_rate": 2.3414634146341463e-05, "loss": 0.4754, "step": 72 }, { "epoch": 0.2959959452610238, "grad_norm": 0.662622678658126, "learning_rate": 2.3739837398373985e-05, "loss": 0.4977, "step": 73 }, { "epoch": 0.3000506842372022, "grad_norm": 0.9453398310013755, "learning_rate": 2.4065040650406507e-05, "loss": 0.4928, "step": 74 }, { "epoch": 0.30410542321338063, "grad_norm": 0.8660901169496351, "learning_rate": 2.4390243902439026e-05, "loss": 0.4852, "step": 75 }, { "epoch": 0.30816016218955905, "grad_norm": 0.7105667914877599, "learning_rate": 2.4715447154471548e-05, "loss": 0.4614, "step": 76 }, { "epoch": 0.31221490116573747, "grad_norm": 0.8440526210631236, "learning_rate": 2.5040650406504066e-05, "loss": 0.4644, "step": 77 }, { "epoch": 0.3162696401419159, "grad_norm": 0.6020973885208171, "learning_rate": 2.536585365853659e-05, "loss": 0.4872, "step": 78 }, { "epoch": 0.32032437911809425, "grad_norm": 0.7023351572827117, "learning_rate": 2.569105691056911e-05, "loss": 0.4738, "step": 79 }, { "epoch": 0.32437911809427267, "grad_norm": 0.6951117408728896, "learning_rate": 2.601626016260163e-05, "loss": 0.4962, "step": 80 }, { "epoch": 0.3284338570704511, "grad_norm": 0.5495147136358052, "learning_rate": 2.634146341463415e-05, "loss": 0.4769, "step": 81 }, { "epoch": 0.3324885960466295, "grad_norm": 0.9580787870118312, "learning_rate": 2.6666666666666667e-05, "loss": 0.4925, "step": 82 }, { "epoch": 0.3365433350228079, "grad_norm": 0.8756426316650179, "learning_rate": 2.699186991869919e-05, "loss": 0.4885, "step": 83 }, { "epoch": 0.34059807399898634, "grad_norm": 0.5128607924822666, "learning_rate": 2.731707317073171e-05, "loss": 0.4821, "step": 84 }, { "epoch": 0.3446528129751647, "grad_norm": 0.7714042013580396, "learning_rate": 2.764227642276423e-05, "loss": 0.4821, "step": 85 }, { "epoch": 0.3487075519513431, "grad_norm": 0.9025242717912816, "learning_rate": 2.796747967479675e-05, "loss": 0.4821, "step": 86 }, { "epoch": 0.35276229092752154, "grad_norm": 0.832105779066487, "learning_rate": 2.829268292682927e-05, "loss": 0.4708, "step": 87 }, { "epoch": 0.35681702990369996, "grad_norm": 0.7568084876237249, "learning_rate": 2.8617886178861792e-05, "loss": 0.4711, "step": 88 }, { "epoch": 0.3608717688798784, "grad_norm": 0.8334252376114408, "learning_rate": 2.8943089430894314e-05, "loss": 0.4715, "step": 89 }, { "epoch": 0.3649265078560568, "grad_norm": 0.7117668340240281, "learning_rate": 2.926829268292683e-05, "loss": 0.4678, "step": 90 }, { "epoch": 0.36898124683223515, "grad_norm": 1.2243295495555375, "learning_rate": 2.959349593495935e-05, "loss": 0.4781, "step": 91 }, { "epoch": 0.3730359858084136, "grad_norm": 0.8296205869900034, "learning_rate": 2.991869918699187e-05, "loss": 0.4766, "step": 92 }, { "epoch": 0.377090724784592, "grad_norm": 0.7539129352053626, "learning_rate": 3.0243902439024392e-05, "loss": 0.4777, "step": 93 }, { "epoch": 0.3811454637607704, "grad_norm": 1.0749389185575666, "learning_rate": 3.056910569105692e-05, "loss": 0.492, "step": 94 }, { "epoch": 0.3852002027369488, "grad_norm": 0.600189634765858, "learning_rate": 3.089430894308943e-05, "loss": 0.4744, "step": 95 }, { "epoch": 0.38925494171312724, "grad_norm": 0.5908203811768996, "learning_rate": 3.1219512195121955e-05, "loss": 0.4621, "step": 96 }, { "epoch": 0.3933096806893056, "grad_norm": 0.5347999775242723, "learning_rate": 3.154471544715447e-05, "loss": 0.4786, "step": 97 }, { "epoch": 0.397364419665484, "grad_norm": 0.7040892357319714, "learning_rate": 3.186991869918699e-05, "loss": 0.474, "step": 98 }, { "epoch": 0.40141915864166244, "grad_norm": 0.6786554961832959, "learning_rate": 3.2195121951219514e-05, "loss": 0.4709, "step": 99 }, { "epoch": 0.40547389761784086, "grad_norm": 0.6937428630099212, "learning_rate": 3.2520325203252037e-05, "loss": 0.4605, "step": 100 }, { "epoch": 0.4095286365940193, "grad_norm": 1.0067934745831473, "learning_rate": 3.284552845528456e-05, "loss": 0.4687, "step": 101 }, { "epoch": 0.41358337557019764, "grad_norm": 0.5630029985204535, "learning_rate": 3.3170731707317074e-05, "loss": 0.4676, "step": 102 }, { "epoch": 0.41763811454637606, "grad_norm": 0.6684928739084679, "learning_rate": 3.3495934959349596e-05, "loss": 0.4764, "step": 103 }, { "epoch": 0.4216928535225545, "grad_norm": 0.8486735179273144, "learning_rate": 3.382113821138212e-05, "loss": 0.466, "step": 104 }, { "epoch": 0.4257475924987329, "grad_norm": 0.8620128202441916, "learning_rate": 3.414634146341463e-05, "loss": 0.4563, "step": 105 }, { "epoch": 0.4298023314749113, "grad_norm": 0.9953116509333751, "learning_rate": 3.4471544715447155e-05, "loss": 0.4625, "step": 106 }, { "epoch": 0.43385707045108973, "grad_norm": 0.8831871462480745, "learning_rate": 3.479674796747968e-05, "loss": 0.48, "step": 107 }, { "epoch": 0.4379118094272681, "grad_norm": 1.0214896844405004, "learning_rate": 3.51219512195122e-05, "loss": 0.4754, "step": 108 }, { "epoch": 0.4419665484034465, "grad_norm": 0.9682087673459563, "learning_rate": 3.544715447154472e-05, "loss": 0.4601, "step": 109 }, { "epoch": 0.44602128737962493, "grad_norm": 0.7911594969242748, "learning_rate": 3.577235772357724e-05, "loss": 0.465, "step": 110 }, { "epoch": 0.45007602635580335, "grad_norm": 0.7275488491297609, "learning_rate": 3.609756097560976e-05, "loss": 0.4529, "step": 111 }, { "epoch": 0.45413076533198177, "grad_norm": 0.5666635082855828, "learning_rate": 3.642276422764228e-05, "loss": 0.4673, "step": 112 }, { "epoch": 0.4581855043081602, "grad_norm": 0.9617899639666891, "learning_rate": 3.67479674796748e-05, "loss": 0.4526, "step": 113 }, { "epoch": 0.46224024328433855, "grad_norm": 0.8929509964367169, "learning_rate": 3.7073170731707325e-05, "loss": 0.4663, "step": 114 }, { "epoch": 0.46629498226051697, "grad_norm": 0.5787808500539665, "learning_rate": 3.739837398373984e-05, "loss": 0.4544, "step": 115 }, { "epoch": 0.4703497212366954, "grad_norm": 0.9536819879255968, "learning_rate": 3.772357723577236e-05, "loss": 0.4541, "step": 116 }, { "epoch": 0.4744044602128738, "grad_norm": 0.8688162376681376, "learning_rate": 3.804878048780488e-05, "loss": 0.4563, "step": 117 }, { "epoch": 0.4784591991890522, "grad_norm": 0.8724746361169373, "learning_rate": 3.83739837398374e-05, "loss": 0.4681, "step": 118 }, { "epoch": 0.48251393816523064, "grad_norm": 0.8844431170442945, "learning_rate": 3.869918699186992e-05, "loss": 0.4696, "step": 119 }, { "epoch": 0.486568677141409, "grad_norm": 0.56855306905161, "learning_rate": 3.9024390243902444e-05, "loss": 0.4736, "step": 120 }, { "epoch": 0.4906234161175874, "grad_norm": 1.0229896700356615, "learning_rate": 3.9349593495934966e-05, "loss": 0.4679, "step": 121 }, { "epoch": 0.49467815509376584, "grad_norm": 1.07910710720519, "learning_rate": 3.967479674796748e-05, "loss": 0.4499, "step": 122 }, { "epoch": 0.49873289406994425, "grad_norm": 0.917601673130554, "learning_rate": 4e-05, "loss": 0.4585, "step": 123 }, { "epoch": 0.5027876330461226, "grad_norm": 0.8747347330902506, "learning_rate": 3.999991946137476e-05, "loss": 0.4588, "step": 124 }, { "epoch": 0.5068423720223011, "grad_norm": 0.8560541390128618, "learning_rate": 3.999967784614766e-05, "loss": 0.461, "step": 125 }, { "epoch": 0.5108971109984795, "grad_norm": 0.9746137302754024, "learning_rate": 3.9999275156264656e-05, "loss": 0.4652, "step": 126 }, { "epoch": 0.5149518499746579, "grad_norm": 0.7772114910947124, "learning_rate": 3.999871139496895e-05, "loss": 0.4637, "step": 127 }, { "epoch": 0.5190065889508363, "grad_norm": 0.8977118713249232, "learning_rate": 3.9997986566800995e-05, "loss": 0.4753, "step": 128 }, { "epoch": 0.5230613279270147, "grad_norm": 0.9293804722058164, "learning_rate": 3.999710067759846e-05, "loss": 0.4638, "step": 129 }, { "epoch": 0.5271160669031931, "grad_norm": 0.6753687683658577, "learning_rate": 3.999605373449617e-05, "loss": 0.463, "step": 130 }, { "epoch": 0.5311708058793715, "grad_norm": 0.6343628396403299, "learning_rate": 3.9994845745926075e-05, "loss": 0.4814, "step": 131 }, { "epoch": 0.53522554485555, "grad_norm": 0.6993598483502492, "learning_rate": 3.999347672161713e-05, "loss": 0.4464, "step": 132 }, { "epoch": 0.5392802838317283, "grad_norm": 0.5720211864839304, "learning_rate": 3.999194667259528e-05, "loss": 0.452, "step": 133 }, { "epoch": 0.5433350228079067, "grad_norm": 0.7415320140841346, "learning_rate": 3.999025561118334e-05, "loss": 0.4632, "step": 134 }, { "epoch": 0.5473897617840852, "grad_norm": 0.6003422772942069, "learning_rate": 3.998840355100086e-05, "loss": 0.4508, "step": 135 }, { "epoch": 0.5514445007602635, "grad_norm": 0.5960022929197948, "learning_rate": 3.998639050696409e-05, "loss": 0.4575, "step": 136 }, { "epoch": 0.555499239736442, "grad_norm": 0.67075514678973, "learning_rate": 3.998421649528582e-05, "loss": 0.4709, "step": 137 }, { "epoch": 0.5595539787126204, "grad_norm": 0.5050245794972739, "learning_rate": 3.9981881533475234e-05, "loss": 0.4552, "step": 138 }, { "epoch": 0.5636087176887988, "grad_norm": 0.6153091919434753, "learning_rate": 3.997938564033779e-05, "loss": 0.4527, "step": 139 }, { "epoch": 0.5676634566649772, "grad_norm": 0.6059714273392856, "learning_rate": 3.9976728835975064e-05, "loss": 0.4563, "step": 140 }, { "epoch": 0.5717181956411556, "grad_norm": 0.5644967288267302, "learning_rate": 3.9973911141784605e-05, "loss": 0.4601, "step": 141 }, { "epoch": 0.575772934617334, "grad_norm": 0.52695863268632, "learning_rate": 3.997093258045973e-05, "loss": 0.4594, "step": 142 }, { "epoch": 0.5798276735935124, "grad_norm": 0.4540070834070039, "learning_rate": 3.996779317598936e-05, "loss": 0.4611, "step": 143 }, { "epoch": 0.5838824125696909, "grad_norm": 0.41883749203462806, "learning_rate": 3.996449295365782e-05, "loss": 0.4607, "step": 144 }, { "epoch": 0.5879371515458692, "grad_norm": 0.4686110759964656, "learning_rate": 3.996103194004467e-05, "loss": 0.4424, "step": 145 }, { "epoch": 0.5919918905220476, "grad_norm": 0.5508486148955315, "learning_rate": 3.995741016302441e-05, "loss": 0.4563, "step": 146 }, { "epoch": 0.5960466294982261, "grad_norm": 0.64023019358397, "learning_rate": 3.9953627651766364e-05, "loss": 0.4578, "step": 147 }, { "epoch": 0.6001013684744044, "grad_norm": 0.5140989991108698, "learning_rate": 3.9949684436734325e-05, "loss": 0.4454, "step": 148 }, { "epoch": 0.6041561074505829, "grad_norm": 0.4340348410597225, "learning_rate": 3.994558054968643e-05, "loss": 0.4634, "step": 149 }, { "epoch": 0.6082108464267613, "grad_norm": 0.48378396586753786, "learning_rate": 3.994131602367481e-05, "loss": 0.4559, "step": 150 }, { "epoch": 0.6122655854029397, "grad_norm": 0.4992950733484296, "learning_rate": 3.9936890893045376e-05, "loss": 0.4496, "step": 151 }, { "epoch": 0.6163203243791181, "grad_norm": 0.5939700069979827, "learning_rate": 3.993230519343752e-05, "loss": 0.4481, "step": 152 }, { "epoch": 0.6203750633552965, "grad_norm": 0.5057787035800353, "learning_rate": 3.992755896178383e-05, "loss": 0.4557, "step": 153 }, { "epoch": 0.6244298023314749, "grad_norm": 0.34945557637485003, "learning_rate": 3.992265223630981e-05, "loss": 0.4476, "step": 154 }, { "epoch": 0.6284845413076533, "grad_norm": 0.44690549300614535, "learning_rate": 3.991758505653355e-05, "loss": 0.4496, "step": 155 }, { "epoch": 0.6325392802838318, "grad_norm": 0.48571154567470315, "learning_rate": 3.991235746326543e-05, "loss": 0.4526, "step": 156 }, { "epoch": 0.6365940192600101, "grad_norm": 0.546664782836717, "learning_rate": 3.9906969498607745e-05, "loss": 0.4395, "step": 157 }, { "epoch": 0.6406487582361885, "grad_norm": 0.49586317059323826, "learning_rate": 3.990142120595444e-05, "loss": 0.4464, "step": 158 }, { "epoch": 0.644703497212367, "grad_norm": 0.4026571772411304, "learning_rate": 3.98957126299907e-05, "loss": 0.4487, "step": 159 }, { "epoch": 0.6487582361885453, "grad_norm": 0.4977604078561742, "learning_rate": 3.9889843816692596e-05, "loss": 0.4603, "step": 160 }, { "epoch": 0.6528129751647238, "grad_norm": 0.5481783621636278, "learning_rate": 3.9883814813326766e-05, "loss": 0.446, "step": 161 }, { "epoch": 0.6568677141409022, "grad_norm": 0.5817240581908952, "learning_rate": 3.9877625668449956e-05, "loss": 0.4471, "step": 162 }, { "epoch": 0.6609224531170805, "grad_norm": 0.6260464538085665, "learning_rate": 3.98712764319087e-05, "loss": 0.4542, "step": 163 }, { "epoch": 0.664977192093259, "grad_norm": 0.5796456786817903, "learning_rate": 3.9864767154838864e-05, "loss": 0.4585, "step": 164 }, { "epoch": 0.6690319310694374, "grad_norm": 0.498824335735083, "learning_rate": 3.9858097889665277e-05, "loss": 0.4363, "step": 165 }, { "epoch": 0.6730866700456158, "grad_norm": 0.6758338142460262, "learning_rate": 3.985126869010129e-05, "loss": 0.4455, "step": 166 }, { "epoch": 0.6771414090217942, "grad_norm": 0.5459072968908438, "learning_rate": 3.984427961114833e-05, "loss": 0.44, "step": 167 }, { "epoch": 0.6811961479979727, "grad_norm": 0.5150078272165399, "learning_rate": 3.9837130709095475e-05, "loss": 0.4466, "step": 168 }, { "epoch": 0.685250886974151, "grad_norm": 0.5297400249429207, "learning_rate": 3.982982204151901e-05, "loss": 0.4391, "step": 169 }, { "epoch": 0.6893056259503294, "grad_norm": 0.5810248751402379, "learning_rate": 3.982235366728193e-05, "loss": 0.4454, "step": 170 }, { "epoch": 0.6933603649265079, "grad_norm": 0.636539014933532, "learning_rate": 3.9814725646533505e-05, "loss": 0.4505, "step": 171 }, { "epoch": 0.6974151039026862, "grad_norm": 0.45467828826050555, "learning_rate": 3.9806938040708746e-05, "loss": 0.4537, "step": 172 }, { "epoch": 0.7014698428788647, "grad_norm": 0.683313881196239, "learning_rate": 3.9798990912527976e-05, "loss": 0.4575, "step": 173 }, { "epoch": 0.7055245818550431, "grad_norm": 0.6166079189571572, "learning_rate": 3.979088432599627e-05, "loss": 0.4439, "step": 174 }, { "epoch": 0.7095793208312214, "grad_norm": 0.4486373626750091, "learning_rate": 3.9782618346402964e-05, "loss": 0.4482, "step": 175 }, { "epoch": 0.7136340598073999, "grad_norm": 0.6147580811992142, "learning_rate": 3.977419304032111e-05, "loss": 0.4527, "step": 176 }, { "epoch": 0.7176887987835783, "grad_norm": 0.49517697899707, "learning_rate": 3.976560847560697e-05, "loss": 0.4444, "step": 177 }, { "epoch": 0.7217435377597567, "grad_norm": 0.44983574935088483, "learning_rate": 3.9756864721399456e-05, "loss": 0.4594, "step": 178 }, { "epoch": 0.7257982767359351, "grad_norm": 0.43280030572115596, "learning_rate": 3.974796184811956e-05, "loss": 0.451, "step": 179 }, { "epoch": 0.7298530157121136, "grad_norm": 0.4874767400947539, "learning_rate": 3.973889992746979e-05, "loss": 0.4339, "step": 180 }, { "epoch": 0.733907754688292, "grad_norm": 0.4922722943570759, "learning_rate": 3.972967903243361e-05, "loss": 0.4599, "step": 181 }, { "epoch": 0.7379624936644703, "grad_norm": 0.5375172656126878, "learning_rate": 3.972029923727486e-05, "loss": 0.4435, "step": 182 }, { "epoch": 0.7420172326406488, "grad_norm": 0.4702543592886448, "learning_rate": 3.971076061753709e-05, "loss": 0.4496, "step": 183 }, { "epoch": 0.7460719716168271, "grad_norm": 0.5440133057820529, "learning_rate": 3.9701063250043066e-05, "loss": 0.4474, "step": 184 }, { "epoch": 0.7501267105930056, "grad_norm": 0.645207429034061, "learning_rate": 3.969120721289402e-05, "loss": 0.4489, "step": 185 }, { "epoch": 0.754181449569184, "grad_norm": 0.5132317581257512, "learning_rate": 3.9681192585469146e-05, "loss": 0.4383, "step": 186 }, { "epoch": 0.7582361885453623, "grad_norm": 0.7098105753066087, "learning_rate": 3.9671019448424865e-05, "loss": 0.4394, "step": 187 }, { "epoch": 0.7622909275215408, "grad_norm": 0.7207350999066172, "learning_rate": 3.966068788369422e-05, "loss": 0.4342, "step": 188 }, { "epoch": 0.7663456664977192, "grad_norm": 0.43303930043968286, "learning_rate": 3.965019797448622e-05, "loss": 0.4441, "step": 189 }, { "epoch": 0.7704004054738977, "grad_norm": 0.7188987735276627, "learning_rate": 3.963954980528515e-05, "loss": 0.4509, "step": 190 }, { "epoch": 0.774455144450076, "grad_norm": 0.5789984255949887, "learning_rate": 3.9628743461849905e-05, "loss": 0.4408, "step": 191 }, { "epoch": 0.7785098834262545, "grad_norm": 0.3997093142186636, "learning_rate": 3.961777903121329e-05, "loss": 0.4394, "step": 192 }, { "epoch": 0.7825646224024329, "grad_norm": 0.6245650496227941, "learning_rate": 3.960665660168131e-05, "loss": 0.4573, "step": 193 }, { "epoch": 0.7866193613786112, "grad_norm": 0.5033896109655852, "learning_rate": 3.9595376262832485e-05, "loss": 0.4398, "step": 194 }, { "epoch": 0.7906741003547897, "grad_norm": 0.5908681880104981, "learning_rate": 3.9583938105517127e-05, "loss": 0.4398, "step": 195 }, { "epoch": 0.794728839330968, "grad_norm": 0.5325968887583044, "learning_rate": 3.957234222185657e-05, "loss": 0.4337, "step": 196 }, { "epoch": 0.7987835783071465, "grad_norm": 0.5112486779963911, "learning_rate": 3.9560588705242474e-05, "loss": 0.452, "step": 197 }, { "epoch": 0.8028383172833249, "grad_norm": 0.5714116556138199, "learning_rate": 3.954867765033605e-05, "loss": 0.4417, "step": 198 }, { "epoch": 0.8068930562595032, "grad_norm": 0.4606788887399649, "learning_rate": 3.953660915306728e-05, "loss": 0.4353, "step": 199 }, { "epoch": 0.8109477952356817, "grad_norm": 0.47735063343672396, "learning_rate": 3.952438331063419e-05, "loss": 0.4442, "step": 200 }, { "epoch": 0.8150025342118601, "grad_norm": 0.43417457536476645, "learning_rate": 3.951200022150205e-05, "loss": 0.4309, "step": 201 }, { "epoch": 0.8190572731880386, "grad_norm": 0.39477778024595883, "learning_rate": 3.949945998540253e-05, "loss": 0.4302, "step": 202 }, { "epoch": 0.8231120121642169, "grad_norm": 0.4228815919760032, "learning_rate": 3.9486762703332993e-05, "loss": 0.4358, "step": 203 }, { "epoch": 0.8271667511403953, "grad_norm": 0.4273575228766973, "learning_rate": 3.947390847755559e-05, "loss": 0.4594, "step": 204 }, { "epoch": 0.8312214901165738, "grad_norm": 0.39921525908455463, "learning_rate": 3.946089741159648e-05, "loss": 0.4344, "step": 205 }, { "epoch": 0.8352762290927521, "grad_norm": 0.5480129192843906, "learning_rate": 3.944772961024501e-05, "loss": 0.4464, "step": 206 }, { "epoch": 0.8393309680689306, "grad_norm": 0.5211890378922015, "learning_rate": 3.943440517955285e-05, "loss": 0.4374, "step": 207 }, { "epoch": 0.843385707045109, "grad_norm": 0.42056708938925036, "learning_rate": 3.9420924226833126e-05, "loss": 0.4324, "step": 208 }, { "epoch": 0.8474404460212874, "grad_norm": 0.5985246715105355, "learning_rate": 3.9407286860659566e-05, "loss": 0.4377, "step": 209 }, { "epoch": 0.8514951849974658, "grad_norm": 0.5907721134613704, "learning_rate": 3.9393493190865657e-05, "loss": 0.4454, "step": 210 }, { "epoch": 0.8555499239736442, "grad_norm": 0.7143584603746486, "learning_rate": 3.937954332854371e-05, "loss": 0.4469, "step": 211 }, { "epoch": 0.8596046629498226, "grad_norm": 0.6259596706855198, "learning_rate": 3.9365437386044016e-05, "loss": 0.4481, "step": 212 }, { "epoch": 0.863659401926001, "grad_norm": 0.45790759044221346, "learning_rate": 3.935117547697387e-05, "loss": 0.4462, "step": 213 }, { "epoch": 0.8677141409021795, "grad_norm": 0.5684588202139279, "learning_rate": 3.933675771619675e-05, "loss": 0.4488, "step": 214 }, { "epoch": 0.8717688798783578, "grad_norm": 0.5207686670878338, "learning_rate": 3.932218421983131e-05, "loss": 0.4443, "step": 215 }, { "epoch": 0.8758236188545362, "grad_norm": 0.5242876187665451, "learning_rate": 3.9307455105250484e-05, "loss": 0.4359, "step": 216 }, { "epoch": 0.8798783578307147, "grad_norm": 0.49735435278664447, "learning_rate": 3.929257049108054e-05, "loss": 0.4426, "step": 217 }, { "epoch": 0.883933096806893, "grad_norm": 0.49662910901358226, "learning_rate": 3.927753049720011e-05, "loss": 0.4393, "step": 218 }, { "epoch": 0.8879878357830715, "grad_norm": 0.5579487535771155, "learning_rate": 3.9262335244739234e-05, "loss": 0.4155, "step": 219 }, { "epoch": 0.8920425747592499, "grad_norm": 0.5410154005218771, "learning_rate": 3.92469848560784e-05, "loss": 0.4332, "step": 220 }, { "epoch": 0.8960973137354283, "grad_norm": 0.42631522032694014, "learning_rate": 3.923147945484751e-05, "loss": 0.4345, "step": 221 }, { "epoch": 0.9001520527116067, "grad_norm": 0.5199464340845822, "learning_rate": 3.9215819165924956e-05, "loss": 0.4364, "step": 222 }, { "epoch": 0.9042067916877851, "grad_norm": 0.5441077032111103, "learning_rate": 3.920000411543654e-05, "loss": 0.4379, "step": 223 }, { "epoch": 0.9082615306639635, "grad_norm": 0.5512337913347046, "learning_rate": 3.9184034430754495e-05, "loss": 0.4458, "step": 224 }, { "epoch": 0.9123162696401419, "grad_norm": 0.3704159262309909, "learning_rate": 3.916791024049648e-05, "loss": 0.4358, "step": 225 }, { "epoch": 0.9163710086163204, "grad_norm": 0.545800344359359, "learning_rate": 3.91516316745245e-05, "loss": 0.453, "step": 226 }, { "epoch": 0.9204257475924987, "grad_norm": 0.559028645187991, "learning_rate": 3.913519886394389e-05, "loss": 0.4405, "step": 227 }, { "epoch": 0.9244804865686771, "grad_norm": 0.445084882476943, "learning_rate": 3.911861194110225e-05, "loss": 0.4369, "step": 228 }, { "epoch": 0.9285352255448556, "grad_norm": 0.38829291025358575, "learning_rate": 3.910187103958837e-05, "loss": 0.4433, "step": 229 }, { "epoch": 0.9325899645210339, "grad_norm": 0.4161046768322844, "learning_rate": 3.908497629423117e-05, "loss": 0.437, "step": 230 }, { "epoch": 0.9366447034972124, "grad_norm": 0.44418169167678184, "learning_rate": 3.9067927841098614e-05, "loss": 0.4411, "step": 231 }, { "epoch": 0.9406994424733908, "grad_norm": 0.3857190556942282, "learning_rate": 3.9050725817496594e-05, "loss": 0.4346, "step": 232 }, { "epoch": 0.9447541814495691, "grad_norm": 0.3769796177377015, "learning_rate": 3.9033370361967844e-05, "loss": 0.4241, "step": 233 }, { "epoch": 0.9488089204257476, "grad_norm": 0.43702784916532017, "learning_rate": 3.901586161429081e-05, "loss": 0.4236, "step": 234 }, { "epoch": 0.952863659401926, "grad_norm": 0.45981855846636044, "learning_rate": 3.8998199715478545e-05, "loss": 0.4442, "step": 235 }, { "epoch": 0.9569183983781044, "grad_norm": 0.4269380321130967, "learning_rate": 3.8980384807777564e-05, "loss": 0.4381, "step": 236 }, { "epoch": 0.9609731373542828, "grad_norm": 0.3971203256106631, "learning_rate": 3.896241703466667e-05, "loss": 0.4432, "step": 237 }, { "epoch": 0.9650278763304613, "grad_norm": 0.3602641520003022, "learning_rate": 3.894429654085585e-05, "loss": 0.4281, "step": 238 }, { "epoch": 0.9690826153066396, "grad_norm": 0.45190002031963666, "learning_rate": 3.892602347228505e-05, "loss": 0.439, "step": 239 }, { "epoch": 0.973137354282818, "grad_norm": 0.46284188327643033, "learning_rate": 3.890759797612307e-05, "loss": 0.418, "step": 240 }, { "epoch": 0.9771920932589965, "grad_norm": 0.45699481404319203, "learning_rate": 3.888902020076632e-05, "loss": 0.4298, "step": 241 }, { "epoch": 0.9812468322351748, "grad_norm": 0.3600975345760478, "learning_rate": 3.887029029583764e-05, "loss": 0.4397, "step": 242 }, { "epoch": 0.9853015712113533, "grad_norm": 0.43366081136895485, "learning_rate": 3.8851408412185125e-05, "loss": 0.4315, "step": 243 }, { "epoch": 0.9893563101875317, "grad_norm": 0.3912892598031057, "learning_rate": 3.8832374701880855e-05, "loss": 0.4291, "step": 244 }, { "epoch": 0.99341104916371, "grad_norm": 0.46090479996052786, "learning_rate": 3.881318931821972e-05, "loss": 0.4537, "step": 245 }, { "epoch": 0.9974657881398885, "grad_norm": 0.39574787228697994, "learning_rate": 3.879385241571817e-05, "loss": 0.4405, "step": 246 }, { "epoch": 1.0025342118601115, "grad_norm": 0.5585851432530806, "learning_rate": 3.8774364150112955e-05, "loss": 0.4257, "step": 247 }, { "epoch": 1.00658895083629, "grad_norm": 0.5288384857074764, "learning_rate": 3.8754724678359884e-05, "loss": 0.3953, "step": 248 }, { "epoch": 1.0106436898124682, "grad_norm": 0.4500001600632361, "learning_rate": 3.873493415863256e-05, "loss": 0.4084, "step": 249 }, { "epoch": 1.0146984287886467, "grad_norm": 0.5664458510716461, "learning_rate": 3.871499275032111e-05, "loss": 0.3946, "step": 250 }, { "epoch": 1.0187531677648252, "grad_norm": 0.4873149670403128, "learning_rate": 3.869490061403091e-05, "loss": 0.4029, "step": 251 }, { "epoch": 1.0228079067410036, "grad_norm": 0.5365113289462207, "learning_rate": 3.867465791158124e-05, "loss": 0.4074, "step": 252 }, { "epoch": 1.0268626457171819, "grad_norm": 0.4499794488289324, "learning_rate": 3.865426480600407e-05, "loss": 0.4113, "step": 253 }, { "epoch": 1.0309173846933604, "grad_norm": 0.46155670794665515, "learning_rate": 3.863372146154264e-05, "loss": 0.4005, "step": 254 }, { "epoch": 1.0349721236695388, "grad_norm": 0.4112299325959544, "learning_rate": 3.861302804365024e-05, "loss": 0.4019, "step": 255 }, { "epoch": 1.039026862645717, "grad_norm": 0.5401068312635213, "learning_rate": 3.85921847189888e-05, "loss": 0.4105, "step": 256 }, { "epoch": 1.0430816016218956, "grad_norm": 0.4793844741962505, "learning_rate": 3.85711916554276e-05, "loss": 0.3883, "step": 257 }, { "epoch": 1.047136340598074, "grad_norm": 0.39735793820442356, "learning_rate": 3.85500490220419e-05, "loss": 0.3901, "step": 258 }, { "epoch": 1.0511910795742525, "grad_norm": 0.5329743507373229, "learning_rate": 3.852875698911154e-05, "loss": 0.4004, "step": 259 }, { "epoch": 1.0552458185504308, "grad_norm": 0.5330577485656234, "learning_rate": 3.850731572811963e-05, "loss": 0.3963, "step": 260 }, { "epoch": 1.0593005575266092, "grad_norm": 0.5112344313496897, "learning_rate": 3.848572541175116e-05, "loss": 0.4017, "step": 261 }, { "epoch": 1.0633552965027877, "grad_norm": 0.5074742848436228, "learning_rate": 3.846398621389154e-05, "loss": 0.3977, "step": 262 }, { "epoch": 1.067410035478966, "grad_norm": 0.3366869871745754, "learning_rate": 3.84420983096253e-05, "loss": 0.394, "step": 263 }, { "epoch": 1.0714647744551444, "grad_norm": 0.5191276318243365, "learning_rate": 3.8420061875234606e-05, "loss": 0.3936, "step": 264 }, { "epoch": 1.075519513431323, "grad_norm": 0.39517330522844585, "learning_rate": 3.839787708819787e-05, "loss": 0.3897, "step": 265 }, { "epoch": 1.0795742524075012, "grad_norm": 0.36615784830929793, "learning_rate": 3.8375544127188325e-05, "loss": 0.3887, "step": 266 }, { "epoch": 1.0836289913836796, "grad_norm": 0.4127504175071635, "learning_rate": 3.8353063172072564e-05, "loss": 0.4007, "step": 267 }, { "epoch": 1.087683730359858, "grad_norm": 0.49948691192437217, "learning_rate": 3.8330434403909105e-05, "loss": 0.3966, "step": 268 }, { "epoch": 1.0917384693360366, "grad_norm": 0.4734222676980367, "learning_rate": 3.8307658004946934e-05, "loss": 0.406, "step": 269 }, { "epoch": 1.0957932083122148, "grad_norm": 0.473490877107583, "learning_rate": 3.8284734158624046e-05, "loss": 0.4011, "step": 270 }, { "epoch": 1.0998479472883933, "grad_norm": 0.39744702830855916, "learning_rate": 3.826166304956594e-05, "loss": 0.4162, "step": 271 }, { "epoch": 1.1039026862645718, "grad_norm": 0.4403404152084597, "learning_rate": 3.8238444863584164e-05, "loss": 0.3949, "step": 272 }, { "epoch": 1.10795742524075, "grad_norm": 0.465759853575892, "learning_rate": 3.821507978767479e-05, "loss": 0.3938, "step": 273 }, { "epoch": 1.1120121642169285, "grad_norm": 0.37761899357011575, "learning_rate": 3.819156801001693e-05, "loss": 0.3894, "step": 274 }, { "epoch": 1.116066903193107, "grad_norm": 0.36520008927865266, "learning_rate": 3.816790971997121e-05, "loss": 0.3945, "step": 275 }, { "epoch": 1.1201216421692854, "grad_norm": 0.9674595271849717, "learning_rate": 3.8144105108078246e-05, "loss": 0.4206, "step": 276 }, { "epoch": 1.1241763811454637, "grad_norm": 0.3989038062115975, "learning_rate": 3.81201543660571e-05, "loss": 0.4044, "step": 277 }, { "epoch": 1.1282311201216422, "grad_norm": 0.39995199186388725, "learning_rate": 3.809605768680377e-05, "loss": 0.402, "step": 278 }, { "epoch": 1.1322858590978206, "grad_norm": 0.44279747962409943, "learning_rate": 3.807181526438958e-05, "loss": 0.3983, "step": 279 }, { "epoch": 1.136340598073999, "grad_norm": 0.4744026457210841, "learning_rate": 3.8047427294059697e-05, "loss": 0.3974, "step": 280 }, { "epoch": 1.1403953370501774, "grad_norm": 0.49236940942093843, "learning_rate": 3.802289397223145e-05, "loss": 0.3842, "step": 281 }, { "epoch": 1.1444500760263558, "grad_norm": 0.4257256765887426, "learning_rate": 3.7998215496492854e-05, "loss": 0.3994, "step": 282 }, { "epoch": 1.1485048150025343, "grad_norm": 0.4921425605815485, "learning_rate": 3.797339206560096e-05, "loss": 0.4065, "step": 283 }, { "epoch": 1.1525595539787126, "grad_norm": 0.5911685952872917, "learning_rate": 3.794842387948027e-05, "loss": 0.3989, "step": 284 }, { "epoch": 1.156614292954891, "grad_norm": 0.7525020902337853, "learning_rate": 3.7923311139221114e-05, "loss": 0.391, "step": 285 }, { "epoch": 1.1606690319310695, "grad_norm": 0.6150425780240992, "learning_rate": 3.7898054047078054e-05, "loss": 0.4005, "step": 286 }, { "epoch": 1.1647237709072478, "grad_norm": 1.0989939653350722, "learning_rate": 3.787265280646825e-05, "loss": 0.4033, "step": 287 }, { "epoch": 1.1687785098834262, "grad_norm": 0.6363395360187993, "learning_rate": 3.7847107621969786e-05, "loss": 0.3965, "step": 288 }, { "epoch": 1.1728332488596047, "grad_norm": 0.6220755464745588, "learning_rate": 3.7821418699320064e-05, "loss": 0.3896, "step": 289 }, { "epoch": 1.1768879878357832, "grad_norm": 0.7449170039708953, "learning_rate": 3.7795586245414145e-05, "loss": 0.4035, "step": 290 }, { "epoch": 1.1809427268119614, "grad_norm": 0.591255417187614, "learning_rate": 3.776961046830306e-05, "loss": 0.3993, "step": 291 }, { "epoch": 1.18499746578814, "grad_norm": 0.6051628651523742, "learning_rate": 3.774349157719215e-05, "loss": 0.4132, "step": 292 }, { "epoch": 1.1890522047643184, "grad_norm": 0.6047117945311438, "learning_rate": 3.7717229782439365e-05, "loss": 0.4051, "step": 293 }, { "epoch": 1.1931069437404966, "grad_norm": 0.5076884917950301, "learning_rate": 3.769082529555359e-05, "loss": 0.4069, "step": 294 }, { "epoch": 1.1971616827166751, "grad_norm": 0.4896939162415218, "learning_rate": 3.766427832919294e-05, "loss": 0.3873, "step": 295 }, { "epoch": 1.2012164216928536, "grad_norm": 0.4807807210562994, "learning_rate": 3.7637589097163024e-05, "loss": 0.388, "step": 296 }, { "epoch": 1.2052711606690318, "grad_norm": 0.4883671692260387, "learning_rate": 3.761075781441526e-05, "loss": 0.4053, "step": 297 }, { "epoch": 1.2093258996452103, "grad_norm": 0.4090526077036118, "learning_rate": 3.75837846970451e-05, "loss": 0.4135, "step": 298 }, { "epoch": 1.2133806386213888, "grad_norm": 0.48035689491603845, "learning_rate": 3.755666996229032e-05, "loss": 0.3937, "step": 299 }, { "epoch": 1.217435377597567, "grad_norm": 0.45865547997879547, "learning_rate": 3.752941382852927e-05, "loss": 0.4055, "step": 300 }, { "epoch": 1.2214901165737455, "grad_norm": 0.3872181690804374, "learning_rate": 3.7502016515279115e-05, "loss": 0.3891, "step": 301 }, { "epoch": 1.225544855549924, "grad_norm": 0.4366003950201163, "learning_rate": 3.7474478243194043e-05, "loss": 0.3985, "step": 302 }, { "epoch": 1.2295995945261025, "grad_norm": 0.3902586838309499, "learning_rate": 3.744679923406351e-05, "loss": 0.3976, "step": 303 }, { "epoch": 1.2336543335022807, "grad_norm": 0.5062217645980607, "learning_rate": 3.741897971081043e-05, "loss": 0.402, "step": 304 }, { "epoch": 1.2377090724784592, "grad_norm": 0.4219567466015048, "learning_rate": 3.739101989748946e-05, "loss": 0.3949, "step": 305 }, { "epoch": 1.2417638114546377, "grad_norm": 1.919814558813416, "learning_rate": 3.7362920019285066e-05, "loss": 0.4021, "step": 306 }, { "epoch": 1.245818550430816, "grad_norm": 0.5885904338867839, "learning_rate": 3.73346803025098e-05, "loss": 0.3924, "step": 307 }, { "epoch": 1.2498732894069944, "grad_norm": 0.7206326683632147, "learning_rate": 3.730630097460247e-05, "loss": 0.3986, "step": 308 }, { "epoch": 1.2539280283831729, "grad_norm": 0.5047083268707097, "learning_rate": 3.727778226412628e-05, "loss": 0.4002, "step": 309 }, { "epoch": 1.2579827673593513, "grad_norm": 0.47152911566639866, "learning_rate": 3.7249124400767006e-05, "loss": 0.4036, "step": 310 }, { "epoch": 1.2620375063355296, "grad_norm": 0.5817507159992747, "learning_rate": 3.722032761533114e-05, "loss": 0.4071, "step": 311 }, { "epoch": 1.266092245311708, "grad_norm": 0.4389681830028791, "learning_rate": 3.719139213974403e-05, "loss": 0.4035, "step": 312 }, { "epoch": 1.2701469842878865, "grad_norm": 0.4861819561512561, "learning_rate": 3.7162318207048006e-05, "loss": 0.3961, "step": 313 }, { "epoch": 1.2742017232640648, "grad_norm": 0.3867527443634877, "learning_rate": 3.713310605140055e-05, "loss": 0.3952, "step": 314 }, { "epoch": 1.2782564622402433, "grad_norm": 0.4515383361357395, "learning_rate": 3.710375590807233e-05, "loss": 0.392, "step": 315 }, { "epoch": 1.2823112012164217, "grad_norm": 0.3891050820405052, "learning_rate": 3.7074268013445365e-05, "loss": 0.403, "step": 316 }, { "epoch": 1.2863659401926002, "grad_norm": 1.5948556672623724, "learning_rate": 3.7044642605011114e-05, "loss": 0.4115, "step": 317 }, { "epoch": 1.2904206791687785, "grad_norm": 0.37686649038650777, "learning_rate": 3.701487992136854e-05, "loss": 0.397, "step": 318 }, { "epoch": 1.294475418144957, "grad_norm": 0.514950550582151, "learning_rate": 3.69849802022222e-05, "loss": 0.3955, "step": 319 }, { "epoch": 1.2985301571211354, "grad_norm": 405.3648355723665, "learning_rate": 3.6954943688380334e-05, "loss": 0.3877, "step": 320 }, { "epoch": 1.3025848960973136, "grad_norm": 3.3264295700283486, "learning_rate": 3.692477062175289e-05, "loss": 0.3984, "step": 321 }, { "epoch": 1.3066396350734921, "grad_norm": 519.0077075298493, "learning_rate": 3.689446124534958e-05, "loss": 7.6853, "step": 322 }, { "epoch": 1.3106943740496706, "grad_norm": 32.525425310368036, "learning_rate": 3.686401580327799e-05, "loss": 0.4256, "step": 323 }, { "epoch": 1.314749113025849, "grad_norm": 9.834392485790293, "learning_rate": 3.683343454074149e-05, "loss": 0.4334, "step": 324 }, { "epoch": 1.3188038520020273, "grad_norm": 1.010577250620433, "learning_rate": 3.6802717704037386e-05, "loss": 0.4263, "step": 325 }, { "epoch": 1.3228585909782058, "grad_norm": 0.8329995650981287, "learning_rate": 3.6771865540554855e-05, "loss": 0.4129, "step": 326 }, { "epoch": 1.3269133299543843, "grad_norm": 0.4758991277811742, "learning_rate": 3.674087829877297e-05, "loss": 0.388, "step": 327 }, { "epoch": 1.3309680689305625, "grad_norm": 0.6988490495033972, "learning_rate": 3.6709756228258735e-05, "loss": 0.3912, "step": 328 }, { "epoch": 1.335022807906741, "grad_norm": 0.5186849827435716, "learning_rate": 3.667849957966501e-05, "loss": 0.4091, "step": 329 }, { "epoch": 1.3390775468829195, "grad_norm": 0.6148447608637885, "learning_rate": 3.6647108604728546e-05, "loss": 0.3917, "step": 330 }, { "epoch": 1.343132285859098, "grad_norm": 0.4781258452724784, "learning_rate": 3.661558355626795e-05, "loss": 0.4051, "step": 331 }, { "epoch": 1.3471870248352762, "grad_norm": 0.5557297953854322, "learning_rate": 3.658392468818163e-05, "loss": 0.4001, "step": 332 }, { "epoch": 1.3512417638114547, "grad_norm": 0.49466539674507853, "learning_rate": 3.655213225544574e-05, "loss": 0.3914, "step": 333 }, { "epoch": 1.355296502787633, "grad_norm": 0.5532733640248012, "learning_rate": 3.652020651411218e-05, "loss": 0.4022, "step": 334 }, { "epoch": 1.3593512417638114, "grad_norm": 0.3991207574976117, "learning_rate": 3.6488147721306474e-05, "loss": 0.4047, "step": 335 }, { "epoch": 1.3634059807399899, "grad_norm": 0.50506384651172, "learning_rate": 3.645595613522574e-05, "loss": 0.3882, "step": 336 }, { "epoch": 1.3674607197161683, "grad_norm": 0.42356581545488803, "learning_rate": 3.642363201513657e-05, "loss": 0.3953, "step": 337 }, { "epoch": 1.3715154586923468, "grad_norm": 0.42970808649850645, "learning_rate": 3.6391175621373006e-05, "loss": 0.3998, "step": 338 }, { "epoch": 1.375570197668525, "grad_norm": 0.47338011735660995, "learning_rate": 3.6358587215334355e-05, "loss": 0.4087, "step": 339 }, { "epoch": 1.3796249366447035, "grad_norm": 0.3916313751658908, "learning_rate": 3.632586705948318e-05, "loss": 0.3969, "step": 340 }, { "epoch": 1.3836796756208818, "grad_norm": 0.44914315700171814, "learning_rate": 3.629301541734311e-05, "loss": 0.3992, "step": 341 }, { "epoch": 1.3877344145970603, "grad_norm": 0.4571185531000885, "learning_rate": 3.626003255349676e-05, "loss": 0.3929, "step": 342 }, { "epoch": 1.3917891535732387, "grad_norm": 0.3801157009826539, "learning_rate": 3.622691873358357e-05, "loss": 0.4055, "step": 343 }, { "epoch": 1.3958438925494172, "grad_norm": 0.4298214232056328, "learning_rate": 3.61936742242977e-05, "loss": 0.3962, "step": 344 }, { "epoch": 1.3998986315255955, "grad_norm": 0.3605511469758305, "learning_rate": 3.6160299293385864e-05, "loss": 0.3799, "step": 345 }, { "epoch": 1.403953370501774, "grad_norm": 0.3693094051953041, "learning_rate": 3.612679420964516e-05, "loss": 0.387, "step": 346 }, { "epoch": 1.4080081094779524, "grad_norm": 0.4069183119125987, "learning_rate": 3.609315924292092e-05, "loss": 0.4065, "step": 347 }, { "epoch": 1.4120628484541307, "grad_norm": 0.3685872893336766, "learning_rate": 3.6059394664104554e-05, "loss": 0.3969, "step": 348 }, { "epoch": 1.4161175874303091, "grad_norm": 0.39930617053032663, "learning_rate": 3.602550074513133e-05, "loss": 0.3976, "step": 349 }, { "epoch": 1.4201723264064876, "grad_norm": 0.3584891255834419, "learning_rate": 3.599147775897822e-05, "loss": 0.3926, "step": 350 }, { "epoch": 1.424227065382666, "grad_norm": 0.3167040087254493, "learning_rate": 3.595732597966167e-05, "loss": 0.3928, "step": 351 }, { "epoch": 1.4282818043588443, "grad_norm": 0.3014710055889988, "learning_rate": 3.592304568223542e-05, "loss": 0.395, "step": 352 }, { "epoch": 1.4323365433350228, "grad_norm": 0.34124701904146304, "learning_rate": 3.588863714278826e-05, "loss": 0.3955, "step": 353 }, { "epoch": 1.4363912823112013, "grad_norm": 0.31804931468533354, "learning_rate": 3.585410063844186e-05, "loss": 0.3888, "step": 354 }, { "epoch": 1.4404460212873795, "grad_norm": 0.38116747415048574, "learning_rate": 3.581943644734846e-05, "loss": 0.4003, "step": 355 }, { "epoch": 1.444500760263558, "grad_norm": 0.34829600787329607, "learning_rate": 3.578464484868869e-05, "loss": 0.3972, "step": 356 }, { "epoch": 1.4485554992397365, "grad_norm": 0.35046091303037635, "learning_rate": 3.5749726122669316e-05, "loss": 0.392, "step": 357 }, { "epoch": 1.452610238215915, "grad_norm": 0.3863193603665688, "learning_rate": 3.5714680550520943e-05, "loss": 0.3983, "step": 358 }, { "epoch": 1.4566649771920932, "grad_norm": 0.31113108659155464, "learning_rate": 3.5679508414495794e-05, "loss": 0.3978, "step": 359 }, { "epoch": 1.4607197161682717, "grad_norm": 0.3592768863948493, "learning_rate": 3.564420999786543e-05, "loss": 0.3898, "step": 360 }, { "epoch": 1.4647744551444501, "grad_norm": 0.3080375598746361, "learning_rate": 3.560878558491842e-05, "loss": 0.3907, "step": 361 }, { "epoch": 1.4688291941206284, "grad_norm": 0.29584615839829814, "learning_rate": 3.5573235460958145e-05, "loss": 0.3934, "step": 362 }, { "epoch": 1.4728839330968069, "grad_norm": 0.3577974789318275, "learning_rate": 3.553755991230039e-05, "loss": 0.3866, "step": 363 }, { "epoch": 1.4769386720729853, "grad_norm": 0.33311417156516276, "learning_rate": 3.5501759226271144e-05, "loss": 0.3968, "step": 364 }, { "epoch": 1.4809934110491638, "grad_norm": 0.36238779619843564, "learning_rate": 3.546583369120419e-05, "loss": 0.4066, "step": 365 }, { "epoch": 1.485048150025342, "grad_norm": 0.2624029374908237, "learning_rate": 3.5429783596438864e-05, "loss": 0.3907, "step": 366 }, { "epoch": 1.4891028890015205, "grad_norm": 0.389126532951345, "learning_rate": 3.539360923231766e-05, "loss": 0.4051, "step": 367 }, { "epoch": 1.4931576279776988, "grad_norm": 0.35397556094322635, "learning_rate": 3.535731089018394e-05, "loss": 0.3905, "step": 368 }, { "epoch": 1.4972123669538773, "grad_norm": 0.3135348803432929, "learning_rate": 3.532088886237956e-05, "loss": 0.3951, "step": 369 }, { "epoch": 1.5012671059300557, "grad_norm": 0.42790716459511174, "learning_rate": 3.528434344224253e-05, "loss": 0.3944, "step": 370 }, { "epoch": 1.5053218449062342, "grad_norm": 0.2994135413083538, "learning_rate": 3.524767492410464e-05, "loss": 0.3995, "step": 371 }, { "epoch": 1.5093765838824127, "grad_norm": 0.33252542916299216, "learning_rate": 3.521088360328908e-05, "loss": 0.39, "step": 372 }, { "epoch": 1.513431322858591, "grad_norm": 0.3199968973768327, "learning_rate": 3.517396977610811e-05, "loss": 0.4016, "step": 373 }, { "epoch": 1.5174860618347694, "grad_norm": 0.30413351284273027, "learning_rate": 3.5136933739860595e-05, "loss": 0.4082, "step": 374 }, { "epoch": 1.5215408008109477, "grad_norm": 0.3334437537926414, "learning_rate": 3.509977579282971e-05, "loss": 0.3936, "step": 375 }, { "epoch": 1.5255955397871261, "grad_norm": 0.32083083909592613, "learning_rate": 3.5062496234280424e-05, "loss": 0.3931, "step": 376 }, { "epoch": 1.5296502787633046, "grad_norm": 0.3701039141389278, "learning_rate": 3.502509536445719e-05, "loss": 0.4009, "step": 377 }, { "epoch": 1.533705017739483, "grad_norm": 0.34652844200007354, "learning_rate": 3.498757348458147e-05, "loss": 0.3895, "step": 378 }, { "epoch": 1.5377597567156616, "grad_norm": 0.406391370567825, "learning_rate": 3.4949930896849324e-05, "loss": 0.4107, "step": 379 }, { "epoch": 1.5418144956918398, "grad_norm": 0.4303423923890709, "learning_rate": 3.491216790442899e-05, "loss": 0.3974, "step": 380 }, { "epoch": 1.5458692346680183, "grad_norm": 0.3405658351334668, "learning_rate": 3.487428481145839e-05, "loss": 0.3891, "step": 381 }, { "epoch": 1.5499239736441965, "grad_norm": 0.3415167872495017, "learning_rate": 3.483628192304278e-05, "loss": 0.39, "step": 382 }, { "epoch": 1.553978712620375, "grad_norm": 0.3182363328776571, "learning_rate": 3.479815954525219e-05, "loss": 0.4084, "step": 383 }, { "epoch": 1.5580334515965535, "grad_norm": 0.3117927427532552, "learning_rate": 3.475991798511899e-05, "loss": 0.3911, "step": 384 }, { "epoch": 1.562088190572732, "grad_norm": 0.37865925051268107, "learning_rate": 3.4721557550635464e-05, "loss": 0.3917, "step": 385 }, { "epoch": 1.5661429295489104, "grad_norm": 0.3494264973881227, "learning_rate": 3.468307855075128e-05, "loss": 0.3912, "step": 386 }, { "epoch": 1.5701976685250887, "grad_norm": 0.37418700329788884, "learning_rate": 3.4644481295371005e-05, "loss": 0.3873, "step": 387 }, { "epoch": 1.5742524075012672, "grad_norm": 0.5111673324036071, "learning_rate": 3.460576609535163e-05, "loss": 0.3989, "step": 388 }, { "epoch": 1.5783071464774454, "grad_norm": 0.32132205310005213, "learning_rate": 3.456693326250006e-05, "loss": 0.3925, "step": 389 }, { "epoch": 1.5823618854536239, "grad_norm": 0.46668322696041353, "learning_rate": 3.452798310957058e-05, "loss": 0.3873, "step": 390 }, { "epoch": 1.5864166244298024, "grad_norm": 0.3336586783414633, "learning_rate": 3.4488915950262386e-05, "loss": 0.3893, "step": 391 }, { "epoch": 1.5904713634059808, "grad_norm": 0.3833888244336963, "learning_rate": 3.4449732099216985e-05, "loss": 0.3855, "step": 392 }, { "epoch": 1.5945261023821593, "grad_norm": 0.3955127629129571, "learning_rate": 3.441043187201574e-05, "loss": 0.3959, "step": 393 }, { "epoch": 1.5985808413583376, "grad_norm": 0.33054491206875664, "learning_rate": 3.437101558517728e-05, "loss": 0.3907, "step": 394 }, { "epoch": 1.6026355803345158, "grad_norm": 0.38500922549082445, "learning_rate": 3.433148355615496e-05, "loss": 0.3956, "step": 395 }, { "epoch": 1.6066903193106943, "grad_norm": 0.3081998007601903, "learning_rate": 3.4291836103334294e-05, "loss": 0.3958, "step": 396 }, { "epoch": 1.6107450582868728, "grad_norm": 0.3651013828181765, "learning_rate": 3.425207354603043e-05, "loss": 0.3979, "step": 397 }, { "epoch": 1.6147997972630512, "grad_norm": 0.3690454617797898, "learning_rate": 3.421219620448553e-05, "loss": 0.3855, "step": 398 }, { "epoch": 1.6188545362392297, "grad_norm": 0.3208276251005485, "learning_rate": 3.417220439986623e-05, "loss": 0.4111, "step": 399 }, { "epoch": 1.622909275215408, "grad_norm": 0.4639196687431776, "learning_rate": 3.4132098454261024e-05, "loss": 0.3971, "step": 400 }, { "epoch": 1.6269640141915864, "grad_norm": 0.3077800597664193, "learning_rate": 3.4091878690677676e-05, "loss": 0.3757, "step": 401 }, { "epoch": 1.6310187531677647, "grad_norm": 0.4213775425730155, "learning_rate": 3.405154543304065e-05, "loss": 0.3948, "step": 402 }, { "epoch": 1.6350734921439432, "grad_norm": 0.3285174605966266, "learning_rate": 3.401109900618843e-05, "loss": 0.3948, "step": 403 }, { "epoch": 1.6391282311201216, "grad_norm": 0.30818303747247144, "learning_rate": 3.3970539735870996e-05, "loss": 0.384, "step": 404 }, { "epoch": 1.6431829700963, "grad_norm": 0.27773259336165657, "learning_rate": 3.392986794874714e-05, "loss": 0.3876, "step": 405 }, { "epoch": 1.6472377090724786, "grad_norm": 0.3263979193679031, "learning_rate": 3.388908397238184e-05, "loss": 0.385, "step": 406 }, { "epoch": 1.6512924480486568, "grad_norm": 0.293831989784571, "learning_rate": 3.384818813524362e-05, "loss": 0.3842, "step": 407 }, { "epoch": 1.6553471870248353, "grad_norm": 0.2777488541464325, "learning_rate": 3.380718076670195e-05, "loss": 0.3996, "step": 408 }, { "epoch": 1.6594019260010135, "grad_norm": 0.32376596110806904, "learning_rate": 3.376606219702454e-05, "loss": 0.3952, "step": 409 }, { "epoch": 1.663456664977192, "grad_norm": 0.37033420154815655, "learning_rate": 3.372483275737468e-05, "loss": 0.385, "step": 410 }, { "epoch": 1.6675114039533705, "grad_norm": 0.2858404688168251, "learning_rate": 3.368349277980861e-05, "loss": 0.3857, "step": 411 }, { "epoch": 1.671566142929549, "grad_norm": 0.38181070271819617, "learning_rate": 3.3642042597272844e-05, "loss": 0.3962, "step": 412 }, { "epoch": 1.6756208819057274, "grad_norm": 0.3450314381248884, "learning_rate": 3.360048254360144e-05, "loss": 0.3835, "step": 413 }, { "epoch": 1.6796756208819057, "grad_norm": 0.27603724947341857, "learning_rate": 3.355881295351336e-05, "loss": 0.3788, "step": 414 }, { "epoch": 1.6837303598580842, "grad_norm": 0.3407591969540205, "learning_rate": 3.351703416260975e-05, "loss": 0.4066, "step": 415 }, { "epoch": 1.6877850988342624, "grad_norm": 0.3129037240508324, "learning_rate": 3.347514650737126e-05, "loss": 0.3873, "step": 416 }, { "epoch": 1.691839837810441, "grad_norm": 0.29362579493779034, "learning_rate": 3.3433150325155295e-05, "loss": 0.3898, "step": 417 }, { "epoch": 1.6958945767866194, "grad_norm": 0.3167098514397954, "learning_rate": 3.339104595419334e-05, "loss": 0.3981, "step": 418 }, { "epoch": 1.6999493157627978, "grad_norm": 0.3524838631653727, "learning_rate": 3.3348833733588204e-05, "loss": 0.4067, "step": 419 }, { "epoch": 1.7040040547389763, "grad_norm": 0.3486718144800517, "learning_rate": 3.3306514003311305e-05, "loss": 0.3955, "step": 420 }, { "epoch": 1.7080587937151546, "grad_norm": 0.35895161838427164, "learning_rate": 3.326408710419996e-05, "loss": 0.3845, "step": 421 }, { "epoch": 1.712113532691333, "grad_norm": 0.3631367875127525, "learning_rate": 3.322155337795454e-05, "loss": 0.4112, "step": 422 }, { "epoch": 1.7161682716675113, "grad_norm": 0.3370624305034817, "learning_rate": 3.317891316713587e-05, "loss": 0.3853, "step": 423 }, { "epoch": 1.7202230106436898, "grad_norm": 0.35444584506711446, "learning_rate": 3.313616681516231e-05, "loss": 0.3949, "step": 424 }, { "epoch": 1.7242777496198682, "grad_norm": 0.3771887168923533, "learning_rate": 3.309331466630713e-05, "loss": 0.3961, "step": 425 }, { "epoch": 1.7283324885960467, "grad_norm": 0.2844208516483471, "learning_rate": 3.305035706569563e-05, "loss": 0.3979, "step": 426 }, { "epoch": 1.7323872275722252, "grad_norm": 0.3680187039214455, "learning_rate": 3.3007294359302433e-05, "loss": 0.3945, "step": 427 }, { "epoch": 1.7364419665484034, "grad_norm": 0.33938970623135983, "learning_rate": 3.296412689394864e-05, "loss": 0.3877, "step": 428 }, { "epoch": 1.7404967055245817, "grad_norm": 0.33206305618775395, "learning_rate": 3.292085501729909e-05, "loss": 0.3893, "step": 429 }, { "epoch": 1.7445514445007602, "grad_norm": 0.3254528336010687, "learning_rate": 3.2877479077859534e-05, "loss": 0.4032, "step": 430 }, { "epoch": 1.7486061834769386, "grad_norm": 0.3587322418438995, "learning_rate": 3.283399942497381e-05, "loss": 0.3773, "step": 431 }, { "epoch": 1.752660922453117, "grad_norm": 0.32710598485094944, "learning_rate": 3.279041640882108e-05, "loss": 0.3906, "step": 432 }, { "epoch": 1.7567156614292956, "grad_norm": 0.36945389732513173, "learning_rate": 3.2746730380412964e-05, "loss": 0.389, "step": 433 }, { "epoch": 1.760770400405474, "grad_norm": 0.3730632148364987, "learning_rate": 3.2702941691590726e-05, "loss": 0.3902, "step": 434 }, { "epoch": 1.7648251393816523, "grad_norm": 0.35281036509801966, "learning_rate": 3.265905069502244e-05, "loss": 0.3993, "step": 435 }, { "epoch": 1.7688798783578306, "grad_norm": 0.3221525756011129, "learning_rate": 3.261505774420016e-05, "loss": 0.3906, "step": 436 }, { "epoch": 1.772934617334009, "grad_norm": 0.4453738017438721, "learning_rate": 3.257096319343707e-05, "loss": 0.3877, "step": 437 }, { "epoch": 1.7769893563101875, "grad_norm": 0.37512620320670587, "learning_rate": 3.2526767397864614e-05, "loss": 0.3977, "step": 438 }, { "epoch": 1.781044095286366, "grad_norm": 0.35895888859822384, "learning_rate": 3.248247071342966e-05, "loss": 0.3862, "step": 439 }, { "epoch": 1.7850988342625445, "grad_norm": 0.3487806817540281, "learning_rate": 3.243807349689161e-05, "loss": 0.3879, "step": 440 }, { "epoch": 1.7891535732387227, "grad_norm": 0.2875938811836573, "learning_rate": 3.2393576105819544e-05, "loss": 0.3811, "step": 441 }, { "epoch": 1.7932083122149012, "grad_norm": 0.30703306975725314, "learning_rate": 3.2348978898589333e-05, "loss": 0.396, "step": 442 }, { "epoch": 1.7972630511910794, "grad_norm": 0.322210451016154, "learning_rate": 3.230428223438075e-05, "loss": 0.3935, "step": 443 }, { "epoch": 1.801317790167258, "grad_norm": 0.30565774619845515, "learning_rate": 3.225948647317459e-05, "loss": 0.3954, "step": 444 }, { "epoch": 1.8053725291434364, "grad_norm": 0.3389480538527071, "learning_rate": 3.2214591975749745e-05, "loss": 0.3969, "step": 445 }, { "epoch": 1.8094272681196149, "grad_norm": 0.2981880796252163, "learning_rate": 3.216959910368034e-05, "loss": 0.3865, "step": 446 }, { "epoch": 1.8134820070957933, "grad_norm": 0.3567089495648592, "learning_rate": 3.212450821933277e-05, "loss": 0.3946, "step": 447 }, { "epoch": 1.8175367460719716, "grad_norm": 0.3490704282101637, "learning_rate": 3.207931968586281e-05, "loss": 0.3974, "step": 448 }, { "epoch": 1.82159148504815, "grad_norm": 0.35444831747371663, "learning_rate": 3.203403386721272e-05, "loss": 0.3847, "step": 449 }, { "epoch": 1.8256462240243283, "grad_norm": 0.36553788311210483, "learning_rate": 3.1988651128108245e-05, "loss": 0.3869, "step": 450 }, { "epoch": 1.8297009630005068, "grad_norm": 0.40651411361676026, "learning_rate": 3.194317183405573e-05, "loss": 0.3947, "step": 451 }, { "epoch": 1.8337557019766852, "grad_norm": 0.36785282894685456, "learning_rate": 3.189759635133914e-05, "loss": 0.389, "step": 452 }, { "epoch": 1.8378104409528637, "grad_norm": 0.40634144312578874, "learning_rate": 3.185192504701718e-05, "loss": 0.3814, "step": 453 }, { "epoch": 1.8418651799290422, "grad_norm": 0.4639896847009337, "learning_rate": 3.1806158288920234e-05, "loss": 0.3797, "step": 454 }, { "epoch": 1.8459199189052204, "grad_norm": 1.0576002455900364, "learning_rate": 3.1760296445647477e-05, "loss": 0.3902, "step": 455 }, { "epoch": 1.849974657881399, "grad_norm": 0.4241987830135212, "learning_rate": 3.1714339886563896e-05, "loss": 0.3994, "step": 456 }, { "epoch": 1.8540293968575772, "grad_norm": 0.3762264679582068, "learning_rate": 3.166828898179731e-05, "loss": 0.3875, "step": 457 }, { "epoch": 1.8580841358337556, "grad_norm": 0.3375113265417812, "learning_rate": 3.162214410223536e-05, "loss": 0.3835, "step": 458 }, { "epoch": 1.8621388748099341, "grad_norm": 0.35283164959959806, "learning_rate": 3.157590561952257e-05, "loss": 0.3852, "step": 459 }, { "epoch": 1.8661936137861126, "grad_norm": 0.473601358930604, "learning_rate": 3.152957390605732e-05, "loss": 0.4001, "step": 460 }, { "epoch": 1.870248352762291, "grad_norm": 0.3483620509022687, "learning_rate": 3.148314933498886e-05, "loss": 0.3999, "step": 461 }, { "epoch": 1.8743030917384693, "grad_norm": 0.36689767397741124, "learning_rate": 3.143663228021431e-05, "loss": 0.3725, "step": 462 }, { "epoch": 1.8783578307146478, "grad_norm": 0.306481902190726, "learning_rate": 3.1390023116375624e-05, "loss": 0.384, "step": 463 }, { "epoch": 1.882412569690826, "grad_norm": 0.34169599687605834, "learning_rate": 3.134332221885661e-05, "loss": 0.3822, "step": 464 }, { "epoch": 1.8864673086670045, "grad_norm": 0.326372120220965, "learning_rate": 3.129652996377987e-05, "loss": 0.3848, "step": 465 }, { "epoch": 1.890522047643183, "grad_norm": 0.38479758034303824, "learning_rate": 3.12496467280038e-05, "loss": 0.3849, "step": 466 }, { "epoch": 1.8945767866193615, "grad_norm": 0.32919779377270186, "learning_rate": 3.120267288911952e-05, "loss": 0.3921, "step": 467 }, { "epoch": 1.89863152559554, "grad_norm": 0.410029150617083, "learning_rate": 3.11556088254479e-05, "loss": 0.3955, "step": 468 }, { "epoch": 1.9026862645717182, "grad_norm": 0.3285069930724247, "learning_rate": 3.11084549160364e-05, "loss": 0.385, "step": 469 }, { "epoch": 1.9067410035478964, "grad_norm": 0.4128587107811951, "learning_rate": 3.106121154065615e-05, "loss": 0.3924, "step": 470 }, { "epoch": 1.910795742524075, "grad_norm": 0.3662623833954398, "learning_rate": 3.1013879079798805e-05, "loss": 0.3809, "step": 471 }, { "epoch": 1.9148504815002534, "grad_norm": 0.3070669078745816, "learning_rate": 3.096645791467348e-05, "loss": 0.3883, "step": 472 }, { "epoch": 1.9189052204764319, "grad_norm": 0.36583129890784066, "learning_rate": 3.091894842720373e-05, "loss": 0.3951, "step": 473 }, { "epoch": 1.9229599594526103, "grad_norm": 0.3367300009350626, "learning_rate": 3.0871351000024425e-05, "loss": 0.3712, "step": 474 }, { "epoch": 1.9270146984287888, "grad_norm": 0.3385770044719278, "learning_rate": 3.0823666016478716e-05, "loss": 0.392, "step": 475 }, { "epoch": 1.931069437404967, "grad_norm": 0.3387919175873045, "learning_rate": 3.0775893860614896e-05, "loss": 0.3833, "step": 476 }, { "epoch": 1.9351241763811453, "grad_norm": 0.3253507823488414, "learning_rate": 3.0728034917183336e-05, "loss": 0.3978, "step": 477 }, { "epoch": 1.9391789153573238, "grad_norm": 0.3088046633978263, "learning_rate": 3.06800895716334e-05, "loss": 0.3968, "step": 478 }, { "epoch": 1.9432336543335023, "grad_norm": 0.32033203873912264, "learning_rate": 3.063205821011029e-05, "loss": 0.3885, "step": 479 }, { "epoch": 1.9472883933096807, "grad_norm": 0.29606394664203267, "learning_rate": 3.0583941219452016e-05, "loss": 0.3866, "step": 480 }, { "epoch": 1.9513431322858592, "grad_norm": 0.31021220656860926, "learning_rate": 3.053573898718618e-05, "loss": 0.3903, "step": 481 }, { "epoch": 1.9553978712620375, "grad_norm": 0.3252699958796775, "learning_rate": 3.0487451901526956e-05, "loss": 0.3924, "step": 482 }, { "epoch": 1.959452610238216, "grad_norm": 0.3102384940425903, "learning_rate": 3.0439080351371875e-05, "loss": 0.3879, "step": 483 }, { "epoch": 1.9635073492143942, "grad_norm": 0.3217411391964678, "learning_rate": 3.0390624726298764e-05, "loss": 0.3946, "step": 484 }, { "epoch": 1.9675620881905727, "grad_norm": 0.3613086783839049, "learning_rate": 3.034208541656255e-05, "loss": 0.3864, "step": 485 }, { "epoch": 1.9716168271667511, "grad_norm": 0.2995808558233509, "learning_rate": 3.029346281309218e-05, "loss": 0.3881, "step": 486 }, { "epoch": 1.9756715661429296, "grad_norm": 0.4191187430012884, "learning_rate": 3.0244757307487415e-05, "loss": 0.3932, "step": 487 }, { "epoch": 1.979726305119108, "grad_norm": 0.35100182082644915, "learning_rate": 3.019596929201569e-05, "loss": 0.3856, "step": 488 }, { "epoch": 1.9837810440952863, "grad_norm": 0.3669298042554506, "learning_rate": 3.0147099159608985e-05, "loss": 0.3775, "step": 489 }, { "epoch": 1.9878357830714648, "grad_norm": 0.33219914759573543, "learning_rate": 3.0098147303860616e-05, "loss": 0.3828, "step": 490 }, { "epoch": 1.991890522047643, "grad_norm": 0.3872915800825817, "learning_rate": 3.0049114119022117e-05, "loss": 0.3933, "step": 491 }, { "epoch": 1.9959452610238215, "grad_norm": 0.34940895816409767, "learning_rate": 3.0000000000000004e-05, "loss": 0.3812, "step": 492 }, { "epoch": 2.0010136847440445, "grad_norm": 0.3508303207810859, "learning_rate": 2.995080534235264e-05, "loss": 0.3697, "step": 493 }, { "epoch": 2.005068423720223, "grad_norm": 0.3786961697618708, "learning_rate": 2.9901530542287044e-05, "loss": 0.3321, "step": 494 }, { "epoch": 2.0091231626964015, "grad_norm": 0.518184560046016, "learning_rate": 2.9852175996655676e-05, "loss": 0.3438, "step": 495 }, { "epoch": 2.01317790167258, "grad_norm": 0.4198214032495236, "learning_rate": 2.980274210295326e-05, "loss": 0.3459, "step": 496 }, { "epoch": 2.0172326406487584, "grad_norm": 0.3817724156762775, "learning_rate": 2.9753229259313578e-05, "loss": 0.332, "step": 497 }, { "epoch": 2.0212873796249364, "grad_norm": 0.4079632769361553, "learning_rate": 2.9703637864506274e-05, "loss": 0.3394, "step": 498 }, { "epoch": 2.025342118601115, "grad_norm": 0.33595895334610326, "learning_rate": 2.965396831793362e-05, "loss": 0.3329, "step": 499 }, { "epoch": 2.0293968575772934, "grad_norm": 0.4168883556409647, "learning_rate": 2.9604221019627316e-05, "loss": 0.3454, "step": 500 }, { "epoch": 2.033451596553472, "grad_norm": 0.35237394342205125, "learning_rate": 2.955439637024526e-05, "loss": 0.3409, "step": 501 }, { "epoch": 2.0375063355296503, "grad_norm": 0.42674102084256915, "learning_rate": 2.9504494771068334e-05, "loss": 0.3441, "step": 502 }, { "epoch": 2.041561074505829, "grad_norm": 0.3797110430608889, "learning_rate": 2.9454516623997156e-05, "loss": 0.3375, "step": 503 }, { "epoch": 2.0456158134820073, "grad_norm": 0.4403483654094071, "learning_rate": 2.9404462331548847e-05, "loss": 0.3479, "step": 504 }, { "epoch": 2.0496705524581853, "grad_norm": 0.34099112737444137, "learning_rate": 2.93543322968538e-05, "loss": 0.3344, "step": 505 }, { "epoch": 2.0537252914343638, "grad_norm": 0.39630213613736276, "learning_rate": 2.9304126923652428e-05, "loss": 0.3414, "step": 506 }, { "epoch": 2.0577800304105422, "grad_norm": 0.3456602895210323, "learning_rate": 2.9253846616291896e-05, "loss": 0.3444, "step": 507 }, { "epoch": 2.0618347693867207, "grad_norm": 0.4043118847031682, "learning_rate": 2.9203491779722896e-05, "loss": 0.3416, "step": 508 }, { "epoch": 2.065889508362899, "grad_norm": 0.3125454353054577, "learning_rate": 2.9153062819496357e-05, "loss": 0.3488, "step": 509 }, { "epoch": 2.0699442473390777, "grad_norm": 0.3829657605563731, "learning_rate": 2.9102560141760178e-05, "loss": 0.3329, "step": 510 }, { "epoch": 2.073998986315256, "grad_norm": 0.38617597055051495, "learning_rate": 2.9051984153256004e-05, "loss": 0.333, "step": 511 }, { "epoch": 2.078053725291434, "grad_norm": 0.3681548639751044, "learning_rate": 2.900133526131588e-05, "loss": 0.3443, "step": 512 }, { "epoch": 2.0821084642676126, "grad_norm": 0.42808529702135667, "learning_rate": 2.8950613873859025e-05, "loss": 0.3382, "step": 513 }, { "epoch": 2.086163203243791, "grad_norm": 0.36345868372940543, "learning_rate": 2.8899820399388515e-05, "loss": 0.3389, "step": 514 }, { "epoch": 2.0902179422199696, "grad_norm": 0.3548685248296975, "learning_rate": 2.8848955246988012e-05, "loss": 0.3392, "step": 515 }, { "epoch": 2.094272681196148, "grad_norm": 0.2936679662425334, "learning_rate": 2.879801882631847e-05, "loss": 0.3331, "step": 516 }, { "epoch": 2.0983274201723265, "grad_norm": 0.33680136575027353, "learning_rate": 2.8747011547614808e-05, "loss": 0.3363, "step": 517 }, { "epoch": 2.102382159148505, "grad_norm": 0.2985755738952556, "learning_rate": 2.8695933821682635e-05, "loss": 0.3423, "step": 518 }, { "epoch": 2.106436898124683, "grad_norm": 0.3264456539813269, "learning_rate": 2.864478605989494e-05, "loss": 0.3344, "step": 519 }, { "epoch": 2.1104916371008615, "grad_norm": 0.31212037879622695, "learning_rate": 2.8593568674188765e-05, "loss": 0.3367, "step": 520 }, { "epoch": 2.11454637607704, "grad_norm": 0.3272914311475285, "learning_rate": 2.8542282077061892e-05, "loss": 0.3496, "step": 521 }, { "epoch": 2.1186011150532185, "grad_norm": 0.2677296470076511, "learning_rate": 2.8490926681569523e-05, "loss": 0.3316, "step": 522 }, { "epoch": 2.122655854029397, "grad_norm": 0.32029923825742684, "learning_rate": 2.8439502901320956e-05, "loss": 0.3288, "step": 523 }, { "epoch": 2.1267105930055754, "grad_norm": 0.3075233912227518, "learning_rate": 2.8388011150476237e-05, "loss": 0.3404, "step": 524 }, { "epoch": 2.1307653319817534, "grad_norm": 0.3565358081844509, "learning_rate": 2.8336451843742866e-05, "loss": 0.3297, "step": 525 }, { "epoch": 2.134820070957932, "grad_norm": 0.32907069702326025, "learning_rate": 2.8284825396372387e-05, "loss": 0.3363, "step": 526 }, { "epoch": 2.1388748099341104, "grad_norm": 0.3238625350212453, "learning_rate": 2.8233132224157132e-05, "loss": 0.3443, "step": 527 }, { "epoch": 2.142929548910289, "grad_norm": 0.3147404859522963, "learning_rate": 2.8181372743426805e-05, "loss": 0.3362, "step": 528 }, { "epoch": 2.1469842878864673, "grad_norm": 0.3694122323741381, "learning_rate": 2.8129547371045128e-05, "loss": 0.3459, "step": 529 }, { "epoch": 2.151039026862646, "grad_norm": 0.28426358667095064, "learning_rate": 2.8077656524406534e-05, "loss": 0.3337, "step": 530 }, { "epoch": 2.1550937658388243, "grad_norm": 0.37223660761250976, "learning_rate": 2.802570062143278e-05, "loss": 0.3441, "step": 531 }, { "epoch": 2.1591485048150023, "grad_norm": 0.2829332923813758, "learning_rate": 2.7973680080569555e-05, "loss": 0.3379, "step": 532 }, { "epoch": 2.163203243791181, "grad_norm": 0.35429092912777715, "learning_rate": 2.792159532078314e-05, "loss": 0.3384, "step": 533 }, { "epoch": 2.1672579827673593, "grad_norm": 0.26729007072301053, "learning_rate": 2.7869446761557033e-05, "loss": 0.3392, "step": 534 }, { "epoch": 2.1713127217435377, "grad_norm": 0.3962107288011036, "learning_rate": 2.781723482288857e-05, "loss": 0.3571, "step": 535 }, { "epoch": 2.175367460719716, "grad_norm": 0.47244546063078185, "learning_rate": 2.7764959925285517e-05, "loss": 0.3341, "step": 536 }, { "epoch": 2.1794221996958947, "grad_norm": 0.30201166921691014, "learning_rate": 2.771262248976272e-05, "loss": 0.3397, "step": 537 }, { "epoch": 2.183476938672073, "grad_norm": 0.35702078150122996, "learning_rate": 2.7660222937838677e-05, "loss": 0.3453, "step": 538 }, { "epoch": 2.187531677648251, "grad_norm": 0.30171609639487484, "learning_rate": 2.7607761691532186e-05, "loss": 0.3401, "step": 539 }, { "epoch": 2.1915864166244297, "grad_norm": 0.34869641943055374, "learning_rate": 2.7555239173358916e-05, "loss": 0.3351, "step": 540 }, { "epoch": 2.195641155600608, "grad_norm": 0.2955008460396327, "learning_rate": 2.7502655806328e-05, "loss": 0.3481, "step": 541 }, { "epoch": 2.1996958945767866, "grad_norm": 0.32835912315509946, "learning_rate": 2.7450012013938648e-05, "loss": 0.3395, "step": 542 }, { "epoch": 2.203750633552965, "grad_norm": 0.26001813271074753, "learning_rate": 2.739730822017673e-05, "loss": 0.3457, "step": 543 }, { "epoch": 2.2078053725291436, "grad_norm": 0.32202081465187626, "learning_rate": 2.7344544849511355e-05, "loss": 0.3412, "step": 544 }, { "epoch": 2.211860111505322, "grad_norm": 0.29332195553269724, "learning_rate": 2.7291722326891456e-05, "loss": 0.3463, "step": 545 }, { "epoch": 2.2159148504815, "grad_norm": 0.27998926694018167, "learning_rate": 2.723884107774236e-05, "loss": 0.3545, "step": 546 }, { "epoch": 2.2199695894576785, "grad_norm": 0.32602404843059535, "learning_rate": 2.718590152796239e-05, "loss": 0.3349, "step": 547 }, { "epoch": 2.224024328433857, "grad_norm": 0.29907863122978223, "learning_rate": 2.71329041039194e-05, "loss": 0.3402, "step": 548 }, { "epoch": 2.2280790674100355, "grad_norm": 0.33460183468831667, "learning_rate": 2.7079849232447357e-05, "loss": 0.3431, "step": 549 }, { "epoch": 2.232133806386214, "grad_norm": 0.30619883037295836, "learning_rate": 2.7026737340842895e-05, "loss": 0.3409, "step": 550 }, { "epoch": 2.2361885453623924, "grad_norm": 0.28874957840004806, "learning_rate": 2.697356885686189e-05, "loss": 0.3297, "step": 551 }, { "epoch": 2.240243284338571, "grad_norm": 0.34033756781816143, "learning_rate": 2.6920344208716014e-05, "loss": 0.3307, "step": 552 }, { "epoch": 2.244298023314749, "grad_norm": 0.29949904747650885, "learning_rate": 2.6867063825069252e-05, "loss": 0.3429, "step": 553 }, { "epoch": 2.2483527622909274, "grad_norm": 0.28148292024022736, "learning_rate": 2.6813728135034494e-05, "loss": 0.3413, "step": 554 }, { "epoch": 2.252407501267106, "grad_norm": 0.31339210560270697, "learning_rate": 2.6760337568170056e-05, "loss": 0.3378, "step": 555 }, { "epoch": 2.2564622402432843, "grad_norm": 0.3341554715617583, "learning_rate": 2.6706892554476226e-05, "loss": 0.338, "step": 556 }, { "epoch": 2.260516979219463, "grad_norm": 0.2935881797036616, "learning_rate": 2.6653393524391795e-05, "loss": 0.329, "step": 557 }, { "epoch": 2.2645717181956413, "grad_norm": 0.33054003103785184, "learning_rate": 2.6599840908790592e-05, "loss": 0.3472, "step": 558 }, { "epoch": 2.2686264571718198, "grad_norm": 0.27318739710290557, "learning_rate": 2.6546235138978028e-05, "loss": 0.3354, "step": 559 }, { "epoch": 2.272681196147998, "grad_norm": 0.26761859509992986, "learning_rate": 2.6492576646687597e-05, "loss": 0.3406, "step": 560 }, { "epoch": 2.2767359351241763, "grad_norm": 0.28450277844946836, "learning_rate": 2.6438865864077425e-05, "loss": 0.3418, "step": 561 }, { "epoch": 2.2807906741003547, "grad_norm": 0.2994794111482728, "learning_rate": 2.6385103223726766e-05, "loss": 0.3261, "step": 562 }, { "epoch": 2.284845413076533, "grad_norm": 0.29126089531895494, "learning_rate": 2.6331289158632537e-05, "loss": 0.3397, "step": 563 }, { "epoch": 2.2889001520527117, "grad_norm": 0.2951951694161177, "learning_rate": 2.6277424102205817e-05, "loss": 0.3378, "step": 564 }, { "epoch": 2.29295489102889, "grad_norm": 0.28609337266982265, "learning_rate": 2.6223508488268374e-05, "loss": 0.355, "step": 565 }, { "epoch": 2.2970096300050686, "grad_norm": 0.2786880471584787, "learning_rate": 2.6169542751049148e-05, "loss": 0.3541, "step": 566 }, { "epoch": 2.3010643689812467, "grad_norm": 0.2952268338061423, "learning_rate": 2.6115527325180754e-05, "loss": 0.3507, "step": 567 }, { "epoch": 2.305119107957425, "grad_norm": 0.2621331565351294, "learning_rate": 2.606146264569603e-05, "loss": 0.3439, "step": 568 }, { "epoch": 2.3091738469336036, "grad_norm": 0.25849865862337107, "learning_rate": 2.6007349148024447e-05, "loss": 0.343, "step": 569 }, { "epoch": 2.313228585909782, "grad_norm": 0.25357866742627866, "learning_rate": 2.5953187267988694e-05, "loss": 0.3298, "step": 570 }, { "epoch": 2.3172833248859606, "grad_norm": 0.25390399085687104, "learning_rate": 2.5898977441801097e-05, "loss": 0.3394, "step": 571 }, { "epoch": 2.321338063862139, "grad_norm": 0.2755458269476276, "learning_rate": 2.584472010606015e-05, "loss": 0.3388, "step": 572 }, { "epoch": 2.3253928028383175, "grad_norm": 0.2977350641467436, "learning_rate": 2.5790415697746976e-05, "loss": 0.3452, "step": 573 }, { "epoch": 2.3294475418144955, "grad_norm": 0.2899728750951841, "learning_rate": 2.5736064654221808e-05, "loss": 0.345, "step": 574 }, { "epoch": 2.333502280790674, "grad_norm": 0.33776623811403467, "learning_rate": 2.568166741322048e-05, "loss": 0.3406, "step": 575 }, { "epoch": 2.3375570197668525, "grad_norm": 0.2778324941495073, "learning_rate": 2.56272244128509e-05, "loss": 0.3438, "step": 576 }, { "epoch": 2.341611758743031, "grad_norm": 0.3638931283194433, "learning_rate": 2.55727360915895e-05, "loss": 0.3423, "step": 577 }, { "epoch": 2.3456664977192094, "grad_norm": 0.2793813361040831, "learning_rate": 2.5518202888277734e-05, "loss": 0.348, "step": 578 }, { "epoch": 2.349721236695388, "grad_norm": 4.663706961492019, "learning_rate": 2.5463625242118523e-05, "loss": 0.3566, "step": 579 }, { "epoch": 2.3537759756715664, "grad_norm": 0.4061416114361282, "learning_rate": 2.5409003592672723e-05, "loss": 0.3433, "step": 580 }, { "epoch": 2.3578307146477444, "grad_norm": 0.35511149366464534, "learning_rate": 2.535433837985559e-05, "loss": 0.3331, "step": 581 }, { "epoch": 2.361885453623923, "grad_norm": 0.35283148714516055, "learning_rate": 2.529963004393324e-05, "loss": 0.3461, "step": 582 }, { "epoch": 2.3659401926001014, "grad_norm": 0.42371511032127823, "learning_rate": 2.524487902551908e-05, "loss": 0.3324, "step": 583 }, { "epoch": 2.36999493157628, "grad_norm": 0.41122502630276875, "learning_rate": 2.519008576557029e-05, "loss": 0.3489, "step": 584 }, { "epoch": 2.3740496705524583, "grad_norm": 0.34820607858584995, "learning_rate": 2.5135250705384254e-05, "loss": 0.3372, "step": 585 }, { "epoch": 2.3781044095286368, "grad_norm": 0.43899946607076124, "learning_rate": 2.5080374286595007e-05, "loss": 0.3498, "step": 586 }, { "epoch": 2.3821591485048152, "grad_norm": 0.339751655194871, "learning_rate": 2.5025456951169677e-05, "loss": 0.3404, "step": 587 }, { "epoch": 2.3862138874809933, "grad_norm": 0.2982427079071855, "learning_rate": 2.4970499141404942e-05, "loss": 0.3499, "step": 588 }, { "epoch": 2.3902686264571718, "grad_norm": 0.3620132119887962, "learning_rate": 2.491550129992345e-05, "loss": 0.3415, "step": 589 }, { "epoch": 2.3943233654333502, "grad_norm": 0.31435596656151027, "learning_rate": 2.486046386967024e-05, "loss": 0.3284, "step": 590 }, { "epoch": 2.3983781044095287, "grad_norm": 0.3267809940603725, "learning_rate": 2.4805387293909214e-05, "loss": 0.3479, "step": 591 }, { "epoch": 2.402432843385707, "grad_norm": 0.3226772756517495, "learning_rate": 2.4750272016219552e-05, "loss": 0.34, "step": 592 }, { "epoch": 2.4064875823618856, "grad_norm": 0.28321258245461595, "learning_rate": 2.4695118480492114e-05, "loss": 0.3419, "step": 593 }, { "epoch": 2.4105423213380637, "grad_norm": 0.29576159277906655, "learning_rate": 2.4639927130925898e-05, "loss": 0.3369, "step": 594 }, { "epoch": 2.414597060314242, "grad_norm": 0.34960132221788026, "learning_rate": 2.458469841202444e-05, "loss": 0.3346, "step": 595 }, { "epoch": 2.4186517992904206, "grad_norm": 0.27912749174847823, "learning_rate": 2.452943276859226e-05, "loss": 0.3184, "step": 596 }, { "epoch": 2.422706538266599, "grad_norm": 0.4079206844063647, "learning_rate": 2.447413064573125e-05, "loss": 0.3444, "step": 597 }, { "epoch": 2.4267612772427776, "grad_norm": 0.33867599033157464, "learning_rate": 2.4418792488837095e-05, "loss": 0.3445, "step": 598 }, { "epoch": 2.430816016218956, "grad_norm": 0.34281899521074927, "learning_rate": 2.4363418743595713e-05, "loss": 0.3342, "step": 599 }, { "epoch": 2.434870755195134, "grad_norm": 0.3942833926969475, "learning_rate": 2.430800985597963e-05, "loss": 0.3466, "step": 600 }, { "epoch": 2.4389254941713125, "grad_norm": 0.2700153201792643, "learning_rate": 2.4252566272244415e-05, "loss": 0.3353, "step": 601 }, { "epoch": 2.442980233147491, "grad_norm": 0.34421953376944664, "learning_rate": 2.4197088438925063e-05, "loss": 0.3388, "step": 602 }, { "epoch": 2.4470349721236695, "grad_norm": 0.3096238956863937, "learning_rate": 2.4141576802832417e-05, "loss": 0.3368, "step": 603 }, { "epoch": 2.451089711099848, "grad_norm": 0.275929205242204, "learning_rate": 2.408603181104957e-05, "loss": 0.3365, "step": 604 }, { "epoch": 2.4551444500760264, "grad_norm": 0.30746537818712844, "learning_rate": 2.4030453910928245e-05, "loss": 0.3371, "step": 605 }, { "epoch": 2.459199189052205, "grad_norm": 0.2754670291585065, "learning_rate": 2.397484355008521e-05, "loss": 0.3408, "step": 606 }, { "epoch": 2.463253928028383, "grad_norm": 0.3092473876991846, "learning_rate": 2.3919201176398662e-05, "loss": 0.3374, "step": 607 }, { "epoch": 2.4673086670045614, "grad_norm": 0.29171329642149957, "learning_rate": 2.3863527238004633e-05, "loss": 0.3298, "step": 608 }, { "epoch": 2.47136340598074, "grad_norm": 0.3113211762643952, "learning_rate": 2.380782218329337e-05, "loss": 0.3403, "step": 609 }, { "epoch": 2.4754181449569184, "grad_norm": 0.34584372197820246, "learning_rate": 2.3752086460905725e-05, "loss": 0.3263, "step": 610 }, { "epoch": 2.479472883933097, "grad_norm": 0.2906302584274851, "learning_rate": 2.3696320519729544e-05, "loss": 0.3367, "step": 611 }, { "epoch": 2.4835276229092753, "grad_norm": 0.3720543882037844, "learning_rate": 2.3640524808896045e-05, "loss": 0.3325, "step": 612 }, { "epoch": 2.487582361885454, "grad_norm": 0.30743503659952753, "learning_rate": 2.3584699777776222e-05, "loss": 0.3268, "step": 613 }, { "epoch": 2.491637100861632, "grad_norm": 0.3437786593084767, "learning_rate": 2.3528845875977195e-05, "loss": 0.3436, "step": 614 }, { "epoch": 2.4956918398378103, "grad_norm": 0.32071465796526916, "learning_rate": 2.3472963553338614e-05, "loss": 0.3376, "step": 615 }, { "epoch": 2.4997465788139888, "grad_norm": 0.2983648130697356, "learning_rate": 2.341705325992901e-05, "loss": 0.3379, "step": 616 }, { "epoch": 2.5038013177901672, "grad_norm": 0.2802530341749169, "learning_rate": 2.336111544604222e-05, "loss": 0.3319, "step": 617 }, { "epoch": 2.5078560567663457, "grad_norm": 0.2878768453014156, "learning_rate": 2.33051505621937e-05, "loss": 0.3467, "step": 618 }, { "epoch": 2.511910795742524, "grad_norm": 0.3032798405213881, "learning_rate": 2.324915905911693e-05, "loss": 0.3376, "step": 619 }, { "epoch": 2.5159655347187027, "grad_norm": 0.33094808650451835, "learning_rate": 2.319314138775977e-05, "loss": 0.3436, "step": 620 }, { "epoch": 2.5200202736948807, "grad_norm": 0.2564509894063003, "learning_rate": 2.3137097999280856e-05, "loss": 0.3404, "step": 621 }, { "epoch": 2.524075012671059, "grad_norm": 0.35011162760222253, "learning_rate": 2.308102934504593e-05, "loss": 0.3587, "step": 622 }, { "epoch": 2.5281297516472376, "grad_norm": 0.2599228372616515, "learning_rate": 2.3024935876624222e-05, "loss": 0.3359, "step": 623 }, { "epoch": 2.532184490623416, "grad_norm": 0.30552560881956947, "learning_rate": 2.2968818045784813e-05, "loss": 0.3389, "step": 624 }, { "epoch": 2.5362392295995946, "grad_norm": 0.26896686515782353, "learning_rate": 2.2912676304493006e-05, "loss": 0.3345, "step": 625 }, { "epoch": 2.540293968575773, "grad_norm": 0.30227509084338783, "learning_rate": 2.2856511104906668e-05, "loss": 0.3392, "step": 626 }, { "epoch": 2.5443487075519515, "grad_norm": 0.27763693007057716, "learning_rate": 2.2800322899372586e-05, "loss": 0.3445, "step": 627 }, { "epoch": 2.5484034465281296, "grad_norm": 0.26388067398927667, "learning_rate": 2.2744112140422844e-05, "loss": 0.357, "step": 628 }, { "epoch": 2.552458185504308, "grad_norm": 0.29972452922715986, "learning_rate": 2.2687879280771177e-05, "loss": 0.3361, "step": 629 }, { "epoch": 2.5565129244804865, "grad_norm": 0.266213554871634, "learning_rate": 2.26316247733093e-05, "loss": 0.3443, "step": 630 }, { "epoch": 2.560567663456665, "grad_norm": 0.3378289111023594, "learning_rate": 2.257534907110328e-05, "loss": 0.3406, "step": 631 }, { "epoch": 2.5646224024328435, "grad_norm": 0.2613903561835911, "learning_rate": 2.2519052627389882e-05, "loss": 0.3383, "step": 632 }, { "epoch": 2.568677141409022, "grad_norm": 0.28856422845869245, "learning_rate": 2.246273589557294e-05, "loss": 0.3384, "step": 633 }, { "epoch": 2.5727318803852004, "grad_norm": 0.2730418474529217, "learning_rate": 2.240639932921966e-05, "loss": 0.3444, "step": 634 }, { "epoch": 2.5767866193613784, "grad_norm": 0.2701896134450245, "learning_rate": 2.2350043382056995e-05, "loss": 0.3387, "step": 635 }, { "epoch": 2.580841358337557, "grad_norm": 0.25751718186185113, "learning_rate": 2.2293668507968015e-05, "loss": 0.3338, "step": 636 }, { "epoch": 2.5848960973137354, "grad_norm": 0.2648241796640657, "learning_rate": 2.2237275160988186e-05, "loss": 0.3407, "step": 637 }, { "epoch": 2.588950836289914, "grad_norm": 0.2242659717622633, "learning_rate": 2.2180863795301787e-05, "loss": 0.3362, "step": 638 }, { "epoch": 2.5930055752660923, "grad_norm": 0.25012426817331057, "learning_rate": 2.212443486523819e-05, "loss": 0.335, "step": 639 }, { "epoch": 2.597060314242271, "grad_norm": 0.2369784227247615, "learning_rate": 2.2067988825268243e-05, "loss": 0.3326, "step": 640 }, { "epoch": 2.6011150532184493, "grad_norm": 0.2502872910039501, "learning_rate": 2.2011526130000596e-05, "loss": 0.3318, "step": 641 }, { "epoch": 2.6051697921946273, "grad_norm": 0.23103154757569797, "learning_rate": 2.1955047234178038e-05, "loss": 0.349, "step": 642 }, { "epoch": 2.6092245311708058, "grad_norm": 0.2865510773336852, "learning_rate": 2.1898552592673825e-05, "loss": 0.3368, "step": 643 }, { "epoch": 2.6132792701469842, "grad_norm": 0.24156975939648404, "learning_rate": 2.184204266048803e-05, "loss": 0.3291, "step": 644 }, { "epoch": 2.6173340091231627, "grad_norm": 0.2793970643579291, "learning_rate": 2.1785517892743887e-05, "loss": 0.3273, "step": 645 }, { "epoch": 2.621388748099341, "grad_norm": 0.24997132609374315, "learning_rate": 2.17289787446841e-05, "loss": 0.3333, "step": 646 }, { "epoch": 2.6254434870755197, "grad_norm": 0.27315221527731587, "learning_rate": 2.1672425671667198e-05, "loss": 0.3416, "step": 647 }, { "epoch": 2.629498226051698, "grad_norm": 0.25444623736611127, "learning_rate": 2.161585912916385e-05, "loss": 0.3465, "step": 648 }, { "epoch": 2.633552965027876, "grad_norm": 0.2648854951810868, "learning_rate": 2.1559279572753214e-05, "loss": 0.3455, "step": 649 }, { "epoch": 2.6376077040040546, "grad_norm": 0.27428487876718655, "learning_rate": 2.1502687458119268e-05, "loss": 0.3485, "step": 650 }, { "epoch": 2.641662442980233, "grad_norm": 0.3265194057534142, "learning_rate": 2.1446083241047116e-05, "loss": 0.3343, "step": 651 }, { "epoch": 2.6457171819564116, "grad_norm": 0.27480018251749366, "learning_rate": 2.1389467377419333e-05, "loss": 0.3452, "step": 652 }, { "epoch": 2.64977192093259, "grad_norm": 0.3008941860490787, "learning_rate": 2.133284032321232e-05, "loss": 0.3467, "step": 653 }, { "epoch": 2.6538266599087685, "grad_norm": 0.3269299342904607, "learning_rate": 2.1276202534492566e-05, "loss": 0.3511, "step": 654 }, { "epoch": 2.657881398884947, "grad_norm": 0.2749621164661891, "learning_rate": 2.121955446741306e-05, "loss": 0.3373, "step": 655 }, { "epoch": 2.661936137861125, "grad_norm": 0.2964729928106933, "learning_rate": 2.1162896578209517e-05, "loss": 0.3376, "step": 656 }, { "epoch": 2.6659908768373035, "grad_norm": 0.27072041833739113, "learning_rate": 2.1106229323196813e-05, "loss": 0.3428, "step": 657 }, { "epoch": 2.670045615813482, "grad_norm": 0.3138007920245196, "learning_rate": 2.1049553158765214e-05, "loss": 0.3389, "step": 658 }, { "epoch": 2.6741003547896605, "grad_norm": 0.26271895372889426, "learning_rate": 2.0992868541376764e-05, "loss": 0.3417, "step": 659 }, { "epoch": 2.678155093765839, "grad_norm": 0.2824478241666888, "learning_rate": 2.093617592756158e-05, "loss": 0.3424, "step": 660 }, { "epoch": 2.682209832742017, "grad_norm": 0.2546345104474321, "learning_rate": 2.0879475773914167e-05, "loss": 0.3374, "step": 661 }, { "epoch": 2.686264571718196, "grad_norm": 0.2977990251333162, "learning_rate": 2.082276853708978e-05, "loss": 0.3325, "step": 662 }, { "epoch": 2.690319310694374, "grad_norm": 0.3195150680581799, "learning_rate": 2.076605467380071e-05, "loss": 0.3497, "step": 663 }, { "epoch": 2.6943740496705524, "grad_norm": 0.29564356248381546, "learning_rate": 2.0709334640812613e-05, "loss": 0.3356, "step": 664 }, { "epoch": 2.698428788646731, "grad_norm": 0.2841565402533432, "learning_rate": 2.0652608894940824e-05, "loss": 0.3413, "step": 665 }, { "epoch": 2.7024835276229093, "grad_norm": 0.31351354818733135, "learning_rate": 2.0595877893046722e-05, "loss": 0.3478, "step": 666 }, { "epoch": 2.706538266599088, "grad_norm": 0.27495417192716143, "learning_rate": 2.0539142092033985e-05, "loss": 0.3452, "step": 667 }, { "epoch": 2.710593005575266, "grad_norm": 0.2812750122219164, "learning_rate": 2.048240194884496e-05, "loss": 0.341, "step": 668 }, { "epoch": 2.7146477445514448, "grad_norm": 0.2756865418288987, "learning_rate": 2.042565792045695e-05, "loss": 0.3565, "step": 669 }, { "epoch": 2.718702483527623, "grad_norm": 0.2473061571971388, "learning_rate": 2.036891046387857e-05, "loss": 0.3365, "step": 670 }, { "epoch": 2.7227572225038013, "grad_norm": 0.28881659802589105, "learning_rate": 2.0312160036146036e-05, "loss": 0.3423, "step": 671 }, { "epoch": 2.7268119614799797, "grad_norm": 0.26889923937670374, "learning_rate": 2.025540709431948e-05, "loss": 0.343, "step": 672 }, { "epoch": 2.730866700456158, "grad_norm": 0.2529313299857496, "learning_rate": 2.0198652095479298e-05, "loss": 0.3427, "step": 673 }, { "epoch": 2.7349214394323367, "grad_norm": 0.24424954657479425, "learning_rate": 2.014189549672245e-05, "loss": 0.3356, "step": 674 }, { "epoch": 2.7389761784085147, "grad_norm": 0.24697674861634025, "learning_rate": 2.0085137755158776e-05, "loss": 0.3452, "step": 675 }, { "epoch": 2.7430309173846936, "grad_norm": 0.2619060070062048, "learning_rate": 2.0028379327907327e-05, "loss": 0.3361, "step": 676 }, { "epoch": 2.7470856563608717, "grad_norm": 0.2289372955011733, "learning_rate": 1.9971620672092676e-05, "loss": 0.3369, "step": 677 }, { "epoch": 2.75114039533705, "grad_norm": 0.23311079589835798, "learning_rate": 1.991486224484123e-05, "loss": 0.3535, "step": 678 }, { "epoch": 2.7551951343132286, "grad_norm": 0.2522823261773414, "learning_rate": 1.985810450327756e-05, "loss": 0.3439, "step": 679 }, { "epoch": 2.759249873289407, "grad_norm": 0.24518391130224162, "learning_rate": 1.9801347904520706e-05, "loss": 0.3396, "step": 680 }, { "epoch": 2.7633046122655855, "grad_norm": 0.2240407246336261, "learning_rate": 1.974459290568053e-05, "loss": 0.3488, "step": 681 }, { "epoch": 2.7673593512417636, "grad_norm": 0.25843520525125774, "learning_rate": 1.968783996385397e-05, "loss": 0.3329, "step": 682 }, { "epoch": 2.7714140902179425, "grad_norm": 0.21593048774346357, "learning_rate": 1.963108953612143e-05, "loss": 0.3355, "step": 683 }, { "epoch": 2.7754688291941205, "grad_norm": 0.27960527041088734, "learning_rate": 1.9574342079543056e-05, "loss": 0.3371, "step": 684 }, { "epoch": 2.779523568170299, "grad_norm": 0.2276247567271468, "learning_rate": 1.9517598051155046e-05, "loss": 0.3423, "step": 685 }, { "epoch": 2.7835783071464775, "grad_norm": 0.2423048067458247, "learning_rate": 1.9460857907966025e-05, "loss": 0.3377, "step": 686 }, { "epoch": 2.787633046122656, "grad_norm": 0.262210073695163, "learning_rate": 1.9404122106953285e-05, "loss": 0.3405, "step": 687 }, { "epoch": 2.7916877850988344, "grad_norm": 0.22253386235581094, "learning_rate": 1.9347391105059176e-05, "loss": 0.3363, "step": 688 }, { "epoch": 2.7957425240750124, "grad_norm": 0.25153807474052087, "learning_rate": 1.92906653591874e-05, "loss": 0.3496, "step": 689 }, { "epoch": 2.799797263051191, "grad_norm": 0.24843382385958218, "learning_rate": 1.9233945326199295e-05, "loss": 0.333, "step": 690 }, { "epoch": 2.8038520020273694, "grad_norm": 0.24041082176195627, "learning_rate": 1.917723146291022e-05, "loss": 0.3314, "step": 691 }, { "epoch": 2.807906741003548, "grad_norm": 0.2774408082402156, "learning_rate": 1.912052422608584e-05, "loss": 0.3396, "step": 692 }, { "epoch": 2.8119614799797263, "grad_norm": 0.24898909905764496, "learning_rate": 1.9063824072438428e-05, "loss": 0.3465, "step": 693 }, { "epoch": 2.816016218955905, "grad_norm": 0.24378998862354342, "learning_rate": 1.9007131458623246e-05, "loss": 0.3338, "step": 694 }, { "epoch": 2.8200709579320833, "grad_norm": 0.2494572327420872, "learning_rate": 1.895044684123479e-05, "loss": 0.3375, "step": 695 }, { "epoch": 2.8241256969082613, "grad_norm": 0.29430403983088477, "learning_rate": 1.8893770676803194e-05, "loss": 0.343, "step": 696 }, { "epoch": 2.82818043588444, "grad_norm": 0.255106665057429, "learning_rate": 1.8837103421790486e-05, "loss": 0.3413, "step": 697 }, { "epoch": 2.8322351748606183, "grad_norm": 0.2811396712093544, "learning_rate": 1.8780445532586952e-05, "loss": 0.338, "step": 698 }, { "epoch": 2.8362899138367967, "grad_norm": 0.24950392283432035, "learning_rate": 1.872379746550743e-05, "loss": 0.3386, "step": 699 }, { "epoch": 2.840344652812975, "grad_norm": 0.32234267953340673, "learning_rate": 1.866715967678769e-05, "loss": 0.3469, "step": 700 }, { "epoch": 2.8443993917891537, "grad_norm": 0.26962099799609596, "learning_rate": 1.861053262258067e-05, "loss": 0.3376, "step": 701 }, { "epoch": 2.848454130765332, "grad_norm": 0.3187121610940054, "learning_rate": 1.8553916758952897e-05, "loss": 0.3445, "step": 702 }, { "epoch": 2.85250886974151, "grad_norm": 0.26232270581243006, "learning_rate": 1.8497312541880735e-05, "loss": 0.333, "step": 703 }, { "epoch": 2.8565636087176887, "grad_norm": 0.34705958385633123, "learning_rate": 1.8440720427246786e-05, "loss": 0.3344, "step": 704 }, { "epoch": 2.860618347693867, "grad_norm": 0.25893925873917617, "learning_rate": 1.8384140870836157e-05, "loss": 0.348, "step": 705 }, { "epoch": 2.8646730866700456, "grad_norm": 0.317778043506264, "learning_rate": 1.8327574328332806e-05, "loss": 0.3362, "step": 706 }, { "epoch": 2.868727825646224, "grad_norm": 0.25879674532917324, "learning_rate": 1.8271021255315906e-05, "loss": 0.334, "step": 707 }, { "epoch": 2.8727825646224026, "grad_norm": 0.24022287051701927, "learning_rate": 1.8214482107256117e-05, "loss": 0.3253, "step": 708 }, { "epoch": 2.876837303598581, "grad_norm": 0.24037942436181955, "learning_rate": 1.8157957339511968e-05, "loss": 0.3491, "step": 709 }, { "epoch": 2.880892042574759, "grad_norm": 0.2532916654498422, "learning_rate": 1.8101447407326182e-05, "loss": 0.3415, "step": 710 }, { "epoch": 2.8849467815509375, "grad_norm": 0.23977626072624197, "learning_rate": 1.8044952765821966e-05, "loss": 0.3392, "step": 711 }, { "epoch": 2.889001520527116, "grad_norm": 0.26732706638090337, "learning_rate": 1.7988473869999407e-05, "loss": 0.3312, "step": 712 }, { "epoch": 2.8930562595032945, "grad_norm": 0.2493797681880144, "learning_rate": 1.7932011174731764e-05, "loss": 0.3421, "step": 713 }, { "epoch": 2.897110998479473, "grad_norm": 0.3018653212957572, "learning_rate": 1.7875565134761817e-05, "loss": 0.3278, "step": 714 }, { "epoch": 2.9011657374556514, "grad_norm": 0.24442378872162296, "learning_rate": 1.7819136204698226e-05, "loss": 0.3426, "step": 715 }, { "epoch": 2.90522047643183, "grad_norm": 0.27422002966274495, "learning_rate": 1.776272483901182e-05, "loss": 0.3471, "step": 716 }, { "epoch": 2.909275215408008, "grad_norm": 0.2633782739360728, "learning_rate": 1.7706331492031995e-05, "loss": 0.3483, "step": 717 }, { "epoch": 2.9133299543841864, "grad_norm": 0.28226324854902607, "learning_rate": 1.764995661794301e-05, "loss": 0.3369, "step": 718 }, { "epoch": 2.917384693360365, "grad_norm": 0.23474582785488665, "learning_rate": 1.759360067078035e-05, "loss": 0.3402, "step": 719 }, { "epoch": 2.9214394323365434, "grad_norm": 0.2422778992491024, "learning_rate": 1.7537264104427064e-05, "loss": 0.339, "step": 720 }, { "epoch": 2.925494171312722, "grad_norm": 0.26602323869654293, "learning_rate": 1.748094737261012e-05, "loss": 0.3436, "step": 721 }, { "epoch": 2.9295489102889003, "grad_norm": 0.23945867586529848, "learning_rate": 1.7424650928896726e-05, "loss": 0.3343, "step": 722 }, { "epoch": 2.9336036492650788, "grad_norm": 0.27497218945375634, "learning_rate": 1.7368375226690712e-05, "loss": 0.3393, "step": 723 }, { "epoch": 2.937658388241257, "grad_norm": 0.24762701129515574, "learning_rate": 1.731212071922883e-05, "loss": 0.3257, "step": 724 }, { "epoch": 2.9417131272174353, "grad_norm": 0.254104045751923, "learning_rate": 1.7255887859577156e-05, "loss": 0.3416, "step": 725 }, { "epoch": 2.9457678661936137, "grad_norm": 0.2423442919073822, "learning_rate": 1.7199677100627427e-05, "loss": 0.3376, "step": 726 }, { "epoch": 2.9498226051697922, "grad_norm": 0.24142234991543235, "learning_rate": 1.7143488895093343e-05, "loss": 0.3387, "step": 727 }, { "epoch": 2.9538773441459707, "grad_norm": 0.22929696749370074, "learning_rate": 1.7087323695506994e-05, "loss": 0.3354, "step": 728 }, { "epoch": 2.957932083122149, "grad_norm": 0.2385370669834686, "learning_rate": 1.7031181954215194e-05, "loss": 0.3358, "step": 729 }, { "epoch": 2.9619868220983276, "grad_norm": 0.2430382113934803, "learning_rate": 1.6975064123375788e-05, "loss": 0.3226, "step": 730 }, { "epoch": 2.9660415610745057, "grad_norm": 0.236682374398441, "learning_rate": 1.6918970654954084e-05, "loss": 0.3324, "step": 731 }, { "epoch": 2.970096300050684, "grad_norm": 1.043825404108531, "learning_rate": 1.686290200071915e-05, "loss": 0.3565, "step": 732 }, { "epoch": 2.9741510390268626, "grad_norm": 0.25416854820711465, "learning_rate": 1.6806858612240234e-05, "loss": 0.3408, "step": 733 }, { "epoch": 2.978205778003041, "grad_norm": 0.2707420453879736, "learning_rate": 1.6750840940883078e-05, "loss": 0.3417, "step": 734 }, { "epoch": 2.9822605169792196, "grad_norm": 0.2695214063924778, "learning_rate": 1.6694849437806305e-05, "loss": 0.3427, "step": 735 }, { "epoch": 2.9863152559553976, "grad_norm": 0.25992493089704044, "learning_rate": 1.663888455395778e-05, "loss": 0.34, "step": 736 }, { "epoch": 2.9903699949315765, "grad_norm": 0.26262911062176664, "learning_rate": 1.6582946740070995e-05, "loss": 0.3343, "step": 737 }, { "epoch": 2.9944247339077545, "grad_norm": 0.2697350675086624, "learning_rate": 1.6527036446661396e-05, "loss": 0.3293, "step": 738 }, { "epoch": 2.998479472883933, "grad_norm": 0.2488379839601312, "learning_rate": 1.6471154124022818e-05, "loss": 0.3281, "step": 739 }, { "epoch": 3.003547896604156, "grad_norm": 0.4038665725555489, "learning_rate": 1.6415300222223788e-05, "loss": 0.299, "step": 740 }, { "epoch": 3.0076026355803345, "grad_norm": 0.6555015977984913, "learning_rate": 1.6359475191103958e-05, "loss": 0.2885, "step": 741 }, { "epoch": 3.011657374556513, "grad_norm": 0.491884111061522, "learning_rate": 1.6303679480270466e-05, "loss": 0.2907, "step": 742 }, { "epoch": 3.0157121135326914, "grad_norm": 0.46219002440972706, "learning_rate": 1.624791353909428e-05, "loss": 0.2906, "step": 743 }, { "epoch": 3.01976685250887, "grad_norm": 0.4327285363760587, "learning_rate": 1.619217781670663e-05, "loss": 0.2822, "step": 744 }, { "epoch": 3.0238215914850484, "grad_norm": 0.311466726291032, "learning_rate": 1.6136472761995373e-05, "loss": 0.2958, "step": 745 }, { "epoch": 3.0278763304612264, "grad_norm": 0.4522347218261994, "learning_rate": 1.608079882360134e-05, "loss": 0.3039, "step": 746 }, { "epoch": 3.031931069437405, "grad_norm": 0.30353181899917236, "learning_rate": 1.60251564499148e-05, "loss": 0.2845, "step": 747 }, { "epoch": 3.0359858084135833, "grad_norm": 0.384398757313169, "learning_rate": 1.596954608907176e-05, "loss": 0.2799, "step": 748 }, { "epoch": 3.040040547389762, "grad_norm": 0.29361375284557906, "learning_rate": 1.591396818895043e-05, "loss": 0.2868, "step": 749 }, { "epoch": 3.0440952863659403, "grad_norm": 0.328952352897174, "learning_rate": 1.585842319716759e-05, "loss": 0.283, "step": 750 }, { "epoch": 3.0481500253421188, "grad_norm": 0.3100213981168211, "learning_rate": 1.5802911561074944e-05, "loss": 0.2952, "step": 751 }, { "epoch": 3.052204764318297, "grad_norm": 0.27457622260440273, "learning_rate": 1.5747433727755595e-05, "loss": 0.294, "step": 752 }, { "epoch": 3.0562595032944753, "grad_norm": 0.29633840161839975, "learning_rate": 1.5691990144020376e-05, "loss": 0.2852, "step": 753 }, { "epoch": 3.0603142422706537, "grad_norm": 0.29631629813692684, "learning_rate": 1.5636581256404297e-05, "loss": 0.28, "step": 754 }, { "epoch": 3.064368981246832, "grad_norm": 0.24698170190677818, "learning_rate": 1.558120751116291e-05, "loss": 0.2779, "step": 755 }, { "epoch": 3.0684237202230107, "grad_norm": 0.2973529584672296, "learning_rate": 1.552586935426876e-05, "loss": 0.2952, "step": 756 }, { "epoch": 3.072478459199189, "grad_norm": 0.25478243998287814, "learning_rate": 1.547056723140774e-05, "loss": 0.3004, "step": 757 }, { "epoch": 3.0765331981753676, "grad_norm": 0.28873488125777896, "learning_rate": 1.5415301587975565e-05, "loss": 0.2862, "step": 758 }, { "epoch": 3.0805879371515457, "grad_norm": 0.2609611876968615, "learning_rate": 1.536007286907411e-05, "loss": 0.2935, "step": 759 }, { "epoch": 3.084642676127724, "grad_norm": 0.2364774416019966, "learning_rate": 1.5304881519507896e-05, "loss": 0.2898, "step": 760 }, { "epoch": 3.0886974151039026, "grad_norm": 0.26399169469907974, "learning_rate": 1.5249727983780453e-05, "loss": 0.292, "step": 761 }, { "epoch": 3.092752154080081, "grad_norm": 0.2652749978433822, "learning_rate": 1.5194612706090786e-05, "loss": 0.2862, "step": 762 }, { "epoch": 3.0968068930562596, "grad_norm": 0.24436721252119287, "learning_rate": 1.5139536130329771e-05, "loss": 0.2859, "step": 763 }, { "epoch": 3.100861632032438, "grad_norm": 0.24527796136210278, "learning_rate": 1.508449870007656e-05, "loss": 0.2916, "step": 764 }, { "epoch": 3.1049163710086165, "grad_norm": 0.260861671223271, "learning_rate": 1.5029500858595056e-05, "loss": 0.2877, "step": 765 }, { "epoch": 3.1089711099847945, "grad_norm": 0.21963274992949533, "learning_rate": 1.4974543048830328e-05, "loss": 0.2877, "step": 766 }, { "epoch": 3.113025848960973, "grad_norm": 0.2605703468220627, "learning_rate": 1.4919625713405e-05, "loss": 0.2828, "step": 767 }, { "epoch": 3.1170805879371515, "grad_norm": 0.24321381866725336, "learning_rate": 1.4864749294615756e-05, "loss": 0.2884, "step": 768 }, { "epoch": 3.12113532691333, "grad_norm": 0.25971678936850046, "learning_rate": 1.4809914234429716e-05, "loss": 0.292, "step": 769 }, { "epoch": 3.1251900658895084, "grad_norm": 0.23044195166742062, "learning_rate": 1.4755120974480923e-05, "loss": 0.3002, "step": 770 }, { "epoch": 3.129244804865687, "grad_norm": 0.23476644344541858, "learning_rate": 1.4700369956066771e-05, "loss": 0.2858, "step": 771 }, { "epoch": 3.1332995438418654, "grad_norm": 0.23801320102359766, "learning_rate": 1.4645661620144413e-05, "loss": 0.2827, "step": 772 }, { "epoch": 3.1373542828180434, "grad_norm": 0.27635445466879544, "learning_rate": 1.4590996407327284e-05, "loss": 0.2937, "step": 773 }, { "epoch": 3.141409021794222, "grad_norm": 0.24731305528308425, "learning_rate": 1.4536374757881487e-05, "loss": 0.2855, "step": 774 }, { "epoch": 3.1454637607704004, "grad_norm": 0.26268177420251204, "learning_rate": 1.4481797111722271e-05, "loss": 0.2725, "step": 775 }, { "epoch": 3.149518499746579, "grad_norm": 0.44459366500052583, "learning_rate": 1.4427263908410507e-05, "loss": 0.2916, "step": 776 }, { "epoch": 3.1535732387227573, "grad_norm": 0.25996227232358626, "learning_rate": 1.4372775587149108e-05, "loss": 0.2915, "step": 777 }, { "epoch": 3.1576279776989358, "grad_norm": 0.24073336565948938, "learning_rate": 1.4318332586779522e-05, "loss": 0.2897, "step": 778 }, { "epoch": 3.1616827166751142, "grad_norm": 0.22594458727185224, "learning_rate": 1.4263935345778202e-05, "loss": 0.2835, "step": 779 }, { "epoch": 3.1657374556512923, "grad_norm": 0.2555812144794195, "learning_rate": 1.420958430225303e-05, "loss": 0.289, "step": 780 }, { "epoch": 3.1697921946274707, "grad_norm": 0.22796177507497437, "learning_rate": 1.415527989393985e-05, "loss": 0.2916, "step": 781 }, { "epoch": 3.1738469336036492, "grad_norm": 0.22237793570594191, "learning_rate": 1.410102255819891e-05, "loss": 0.2952, "step": 782 }, { "epoch": 3.1779016725798277, "grad_norm": 0.20631899771517664, "learning_rate": 1.404681273201131e-05, "loss": 0.2877, "step": 783 }, { "epoch": 3.181956411556006, "grad_norm": 0.22691248823782775, "learning_rate": 1.399265085197556e-05, "loss": 0.2815, "step": 784 }, { "epoch": 3.1860111505321846, "grad_norm": 0.2016074864965494, "learning_rate": 1.393853735430398e-05, "loss": 0.2873, "step": 785 }, { "epoch": 3.1900658895083627, "grad_norm": 0.25947330700829785, "learning_rate": 1.3884472674819246e-05, "loss": 0.2979, "step": 786 }, { "epoch": 3.194120628484541, "grad_norm": 0.20265142046761675, "learning_rate": 1.3830457248950864e-05, "loss": 0.2827, "step": 787 }, { "epoch": 3.1981753674607196, "grad_norm": 0.23490048250729814, "learning_rate": 1.377649151173163e-05, "loss": 0.2876, "step": 788 }, { "epoch": 3.202230106436898, "grad_norm": 0.2287390107960457, "learning_rate": 1.3722575897794181e-05, "loss": 0.2941, "step": 789 }, { "epoch": 3.2062848454130766, "grad_norm": 0.2222038444630793, "learning_rate": 1.3668710841367472e-05, "loss": 0.2934, "step": 790 }, { "epoch": 3.210339584389255, "grad_norm": 0.23370017602071397, "learning_rate": 1.361489677627324e-05, "loss": 0.2931, "step": 791 }, { "epoch": 3.2143943233654335, "grad_norm": 0.2170841378193841, "learning_rate": 1.3561134135922585e-05, "loss": 0.2784, "step": 792 }, { "epoch": 3.2184490623416115, "grad_norm": 0.23330989026811155, "learning_rate": 1.350742335331241e-05, "loss": 0.2878, "step": 793 }, { "epoch": 3.22250380131779, "grad_norm": 0.26212556257614555, "learning_rate": 1.345376486102198e-05, "loss": 0.2838, "step": 794 }, { "epoch": 3.2265585402939685, "grad_norm": 0.26677246163277923, "learning_rate": 1.3400159091209414e-05, "loss": 0.2919, "step": 795 }, { "epoch": 3.230613279270147, "grad_norm": 0.28486036721965935, "learning_rate": 1.3346606475608216e-05, "loss": 0.2968, "step": 796 }, { "epoch": 3.2346680182463254, "grad_norm": 0.25688775270464737, "learning_rate": 1.3293107445523781e-05, "loss": 0.296, "step": 797 }, { "epoch": 3.238722757222504, "grad_norm": 0.2709252455776986, "learning_rate": 1.3239662431829949e-05, "loss": 0.2852, "step": 798 }, { "epoch": 3.2427774961986824, "grad_norm": 0.2555717181267077, "learning_rate": 1.3186271864965509e-05, "loss": 0.2899, "step": 799 }, { "epoch": 3.2468322351748604, "grad_norm": 0.2418715399163598, "learning_rate": 1.3132936174930756e-05, "loss": 0.2916, "step": 800 }, { "epoch": 3.250886974151039, "grad_norm": 0.2372145917557584, "learning_rate": 1.3079655791283995e-05, "loss": 0.2761, "step": 801 }, { "epoch": 3.2549417131272174, "grad_norm": 0.233984253760953, "learning_rate": 1.3026431143138108e-05, "loss": 0.2929, "step": 802 }, { "epoch": 3.258996452103396, "grad_norm": 0.2477590916340065, "learning_rate": 1.2973262659157114e-05, "loss": 0.2917, "step": 803 }, { "epoch": 3.2630511910795743, "grad_norm": 0.23052229537865024, "learning_rate": 1.2920150767552651e-05, "loss": 0.295, "step": 804 }, { "epoch": 3.267105930055753, "grad_norm": 0.22583168822883856, "learning_rate": 1.2867095896080607e-05, "loss": 0.2919, "step": 805 }, { "epoch": 3.2711606690319313, "grad_norm": 0.2268489851901652, "learning_rate": 1.2814098472037612e-05, "loss": 0.2934, "step": 806 }, { "epoch": 3.2752154080081093, "grad_norm": 0.2318396189339719, "learning_rate": 1.276115892225764e-05, "loss": 0.2723, "step": 807 }, { "epoch": 3.2792701469842878, "grad_norm": 0.21364493463091022, "learning_rate": 1.2708277673108555e-05, "loss": 0.296, "step": 808 }, { "epoch": 3.2833248859604662, "grad_norm": 0.22654341902100364, "learning_rate": 1.2655455150488649e-05, "loss": 0.2817, "step": 809 }, { "epoch": 3.2873796249366447, "grad_norm": 0.21231175155954243, "learning_rate": 1.2602691779823272e-05, "loss": 0.2948, "step": 810 }, { "epoch": 3.291434363912823, "grad_norm": 0.21096573562772405, "learning_rate": 1.2549987986061355e-05, "loss": 0.2826, "step": 811 }, { "epoch": 3.2954891028890017, "grad_norm": 0.21021192460686328, "learning_rate": 1.2497344193672005e-05, "loss": 0.2927, "step": 812 }, { "epoch": 3.29954384186518, "grad_norm": 0.22245158734496379, "learning_rate": 1.2444760826641092e-05, "loss": 0.2916, "step": 813 }, { "epoch": 3.303598580841358, "grad_norm": 0.21147829000641263, "learning_rate": 1.2392238308467817e-05, "loss": 0.2923, "step": 814 }, { "epoch": 3.3076533198175366, "grad_norm": 0.2047651769191185, "learning_rate": 1.2339777062161326e-05, "loss": 0.2766, "step": 815 }, { "epoch": 3.311708058793715, "grad_norm": 0.2361262938975103, "learning_rate": 1.2287377510237293e-05, "loss": 0.298, "step": 816 }, { "epoch": 3.3157627977698936, "grad_norm": 0.2277355230765263, "learning_rate": 1.2235040074714488e-05, "loss": 0.2778, "step": 817 }, { "epoch": 3.319817536746072, "grad_norm": 0.21369879072644798, "learning_rate": 1.2182765177111434e-05, "loss": 0.2891, "step": 818 }, { "epoch": 3.3238722757222505, "grad_norm": 0.21234683921963907, "learning_rate": 1.213055323844297e-05, "loss": 0.286, "step": 819 }, { "epoch": 3.327927014698429, "grad_norm": 0.2271560388796642, "learning_rate": 1.2078404679216864e-05, "loss": 0.2865, "step": 820 }, { "epoch": 3.331981753674607, "grad_norm": 0.2489939809209957, "learning_rate": 1.2026319919430458e-05, "loss": 0.2947, "step": 821 }, { "epoch": 3.3360364926507855, "grad_norm": 0.21635730950840532, "learning_rate": 1.1974299378567227e-05, "loss": 0.2921, "step": 822 }, { "epoch": 3.340091231626964, "grad_norm": 0.2274499172044193, "learning_rate": 1.1922343475593462e-05, "loss": 0.2809, "step": 823 }, { "epoch": 3.3441459706031424, "grad_norm": 0.23745418591953887, "learning_rate": 1.187045262895488e-05, "loss": 0.2997, "step": 824 }, { "epoch": 3.348200709579321, "grad_norm": 0.22047674611269633, "learning_rate": 1.1818627256573203e-05, "loss": 0.2846, "step": 825 }, { "epoch": 3.3522554485554994, "grad_norm": 0.2219048708709722, "learning_rate": 1.1766867775842864e-05, "loss": 0.2857, "step": 826 }, { "epoch": 3.356310187531678, "grad_norm": 0.24285532279726313, "learning_rate": 1.1715174603627615e-05, "loss": 0.2871, "step": 827 }, { "epoch": 3.360364926507856, "grad_norm": 0.23335475431628985, "learning_rate": 1.1663548156257147e-05, "loss": 0.2842, "step": 828 }, { "epoch": 3.3644196654840344, "grad_norm": 0.2314497266316077, "learning_rate": 1.161198884952377e-05, "loss": 0.2762, "step": 829 }, { "epoch": 3.368474404460213, "grad_norm": 0.2523385192378258, "learning_rate": 1.1560497098679056e-05, "loss": 0.2863, "step": 830 }, { "epoch": 3.3725291434363913, "grad_norm": 0.2297077185888475, "learning_rate": 1.1509073318430479e-05, "loss": 0.2978, "step": 831 }, { "epoch": 3.37658388241257, "grad_norm": 0.2471619427509842, "learning_rate": 1.1457717922938116e-05, "loss": 0.2875, "step": 832 }, { "epoch": 3.3806386213887483, "grad_norm": 0.24650879120324118, "learning_rate": 1.1406431325811233e-05, "loss": 0.2721, "step": 833 }, { "epoch": 3.3846933603649267, "grad_norm": 0.22502938380682438, "learning_rate": 1.135521394010506e-05, "loss": 0.2887, "step": 834 }, { "epoch": 3.3887480993411048, "grad_norm": 0.2745180146072434, "learning_rate": 1.1304066178317367e-05, "loss": 0.2836, "step": 835 }, { "epoch": 3.3928028383172832, "grad_norm": 0.23669836827694948, "learning_rate": 1.1252988452385199e-05, "loss": 0.2859, "step": 836 }, { "epoch": 3.3968575772934617, "grad_norm": 0.23521117354991083, "learning_rate": 1.1201981173681536e-05, "loss": 0.2931, "step": 837 }, { "epoch": 3.40091231626964, "grad_norm": 0.22655097980066688, "learning_rate": 1.1151044753011991e-05, "loss": 0.2867, "step": 838 }, { "epoch": 3.4049670552458187, "grad_norm": 0.2166071941754023, "learning_rate": 1.1100179600611491e-05, "loss": 0.2895, "step": 839 }, { "epoch": 3.409021794221997, "grad_norm": 0.20799975788693217, "learning_rate": 1.1049386126140985e-05, "loss": 0.2958, "step": 840 }, { "epoch": 3.4130765331981756, "grad_norm": 0.2373639107973486, "learning_rate": 1.0998664738684128e-05, "loss": 0.2841, "step": 841 }, { "epoch": 3.4171312721743536, "grad_norm": 0.2044435213751801, "learning_rate": 1.0948015846744e-05, "loss": 0.2794, "step": 842 }, { "epoch": 3.421186011150532, "grad_norm": 0.22044491131519137, "learning_rate": 1.0897439858239832e-05, "loss": 0.2881, "step": 843 }, { "epoch": 3.4252407501267106, "grad_norm": 0.22805861322756643, "learning_rate": 1.0846937180503652e-05, "loss": 0.2776, "step": 844 }, { "epoch": 3.429295489102889, "grad_norm": 0.21316508017458374, "learning_rate": 1.0796508220277117e-05, "loss": 0.2924, "step": 845 }, { "epoch": 3.4333502280790675, "grad_norm": 0.2210785526868218, "learning_rate": 1.0746153383708107e-05, "loss": 0.2821, "step": 846 }, { "epoch": 3.437404967055246, "grad_norm": 0.22868479207914316, "learning_rate": 1.0695873076347579e-05, "loss": 0.2858, "step": 847 }, { "epoch": 3.441459706031424, "grad_norm": 0.217015714645364, "learning_rate": 1.0645667703146205e-05, "loss": 0.2909, "step": 848 }, { "epoch": 3.4455144450076025, "grad_norm": 0.22684210214468084, "learning_rate": 1.0595537668451161e-05, "loss": 0.2904, "step": 849 }, { "epoch": 3.449569183983781, "grad_norm": 0.22260064936176796, "learning_rate": 1.0545483376002854e-05, "loss": 0.2913, "step": 850 }, { "epoch": 3.4536239229599595, "grad_norm": 0.34975476490382995, "learning_rate": 1.0495505228931676e-05, "loss": 0.2963, "step": 851 }, { "epoch": 3.457678661936138, "grad_norm": 0.2290658877905588, "learning_rate": 1.044560362975474e-05, "loss": 0.2847, "step": 852 }, { "epoch": 3.4617334009123164, "grad_norm": 0.1997702663066045, "learning_rate": 1.0395778980372695e-05, "loss": 0.2898, "step": 853 }, { "epoch": 3.4657881398884944, "grad_norm": 0.22717706868060789, "learning_rate": 1.0346031682066381e-05, "loss": 0.3095, "step": 854 }, { "epoch": 3.469842878864673, "grad_norm": 0.20092085452309635, "learning_rate": 1.0296362135493724e-05, "loss": 0.2827, "step": 855 }, { "epoch": 3.4738976178408514, "grad_norm": 0.2373512287246103, "learning_rate": 1.0246770740686422e-05, "loss": 0.2989, "step": 856 }, { "epoch": 3.47795235681703, "grad_norm": 0.2151615405141435, "learning_rate": 1.0197257897046743e-05, "loss": 0.2865, "step": 857 }, { "epoch": 3.4820070957932083, "grad_norm": 0.2106326008888747, "learning_rate": 1.014782400334433e-05, "loss": 0.2885, "step": 858 }, { "epoch": 3.486061834769387, "grad_norm": 0.2126985882344637, "learning_rate": 1.009846945771296e-05, "loss": 0.2949, "step": 859 }, { "epoch": 3.4901165737455653, "grad_norm": 0.20785874997621984, "learning_rate": 1.0049194657647363e-05, "loss": 0.2864, "step": 860 }, { "epoch": 3.4941713127217433, "grad_norm": 0.22425634746535988, "learning_rate": 1.0000000000000006e-05, "loss": 0.2891, "step": 861 }, { "epoch": 3.498226051697922, "grad_norm": 0.20960014518576967, "learning_rate": 9.950885880977891e-06, "loss": 0.2814, "step": 862 }, { "epoch": 3.5022807906741003, "grad_norm": 0.21676153707793275, "learning_rate": 9.901852696139382e-06, "loss": 0.2823, "step": 863 }, { "epoch": 3.5063355296502787, "grad_norm": 0.24188996839280075, "learning_rate": 9.852900840391027e-06, "loss": 0.2871, "step": 864 }, { "epoch": 3.510390268626457, "grad_norm": 0.20393818468306785, "learning_rate": 9.804030707984313e-06, "loss": 0.2847, "step": 865 }, { "epoch": 3.5144450076026357, "grad_norm": 0.2481292849579236, "learning_rate": 9.755242692512599e-06, "loss": 0.2899, "step": 866 }, { "epoch": 3.518499746578814, "grad_norm": 0.24782279655466669, "learning_rate": 9.70653718690782e-06, "loss": 0.2906, "step": 867 }, { "epoch": 3.522554485554992, "grad_norm": 0.21782850671411005, "learning_rate": 9.657914583437454e-06, "loss": 0.303, "step": 868 }, { "epoch": 3.5266092245311706, "grad_norm": 0.22392036600044954, "learning_rate": 9.609375273701246e-06, "loss": 0.2791, "step": 869 }, { "epoch": 3.530663963507349, "grad_norm": 0.22856703886976665, "learning_rate": 9.560919648628133e-06, "loss": 0.2823, "step": 870 }, { "epoch": 3.5347187024835276, "grad_norm": 0.21321662414902326, "learning_rate": 9.512548098473047e-06, "loss": 0.2907, "step": 871 }, { "epoch": 3.538773441459706, "grad_norm": 0.23010798329682258, "learning_rate": 9.464261012813825e-06, "loss": 0.2941, "step": 872 }, { "epoch": 3.5428281804358845, "grad_norm": 0.21121601889286915, "learning_rate": 9.416058780547987e-06, "loss": 0.2828, "step": 873 }, { "epoch": 3.546882919412063, "grad_norm": 0.21455574160718713, "learning_rate": 9.367941789889714e-06, "loss": 0.2855, "step": 874 }, { "epoch": 3.550937658388241, "grad_norm": 0.21360224730704544, "learning_rate": 9.319910428366607e-06, "loss": 0.294, "step": 875 }, { "epoch": 3.5549923973644195, "grad_norm": 0.23564937541414865, "learning_rate": 9.271965082816667e-06, "loss": 0.2909, "step": 876 }, { "epoch": 3.559047136340598, "grad_norm": 0.2079410311482316, "learning_rate": 9.224106139385111e-06, "loss": 0.289, "step": 877 }, { "epoch": 3.5631018753167765, "grad_norm": 0.22428805786290204, "learning_rate": 9.176333983521291e-06, "loss": 0.2955, "step": 878 }, { "epoch": 3.567156614292955, "grad_norm": 0.20915859070513054, "learning_rate": 9.12864899997558e-06, "loss": 0.2896, "step": 879 }, { "epoch": 3.5712113532691334, "grad_norm": 0.22148067785055595, "learning_rate": 9.08105157279628e-06, "loss": 0.2865, "step": 880 }, { "epoch": 3.575266092245312, "grad_norm": 0.22083711616336463, "learning_rate": 9.03354208532653e-06, "loss": 0.2878, "step": 881 }, { "epoch": 3.57932083122149, "grad_norm": 0.22328553290841555, "learning_rate": 8.986120920201205e-06, "loss": 0.2899, "step": 882 }, { "epoch": 3.5833755701976684, "grad_norm": 0.20257605336014528, "learning_rate": 8.938788459343852e-06, "loss": 0.3, "step": 883 }, { "epoch": 3.587430309173847, "grad_norm": 0.22717695334865742, "learning_rate": 8.8915450839636e-06, "loss": 0.2902, "step": 884 }, { "epoch": 3.5914850481500253, "grad_norm": 0.22787688780291246, "learning_rate": 8.844391174552116e-06, "loss": 0.2911, "step": 885 }, { "epoch": 3.595539787126204, "grad_norm": 0.21293320298258295, "learning_rate": 8.797327110880479e-06, "loss": 0.2816, "step": 886 }, { "epoch": 3.5995945261023823, "grad_norm": 0.21236906993203944, "learning_rate": 8.750353271996206e-06, "loss": 0.2919, "step": 887 }, { "epoch": 3.6036492650785608, "grad_norm": 0.21472057223478905, "learning_rate": 8.703470036220132e-06, "loss": 0.2845, "step": 888 }, { "epoch": 3.607704004054739, "grad_norm": 0.21839388652085914, "learning_rate": 8.656677781143394e-06, "loss": 0.2781, "step": 889 }, { "epoch": 3.6117587430309173, "grad_norm": 0.20452034913801032, "learning_rate": 8.609976883624377e-06, "loss": 0.2781, "step": 890 }, { "epoch": 3.6158134820070957, "grad_norm": 0.19876649634559918, "learning_rate": 8.563367719785698e-06, "loss": 0.29, "step": 891 }, { "epoch": 3.619868220983274, "grad_norm": 0.2229774116444538, "learning_rate": 8.516850665011138e-06, "loss": 0.2896, "step": 892 }, { "epoch": 3.6239229599594527, "grad_norm": 0.1997721214919637, "learning_rate": 8.47042609394269e-06, "loss": 0.2935, "step": 893 }, { "epoch": 3.627977698935631, "grad_norm": 0.18919396264396238, "learning_rate": 8.424094380477432e-06, "loss": 0.2842, "step": 894 }, { "epoch": 3.6320324379118096, "grad_norm": 0.21078882577642255, "learning_rate": 8.37785589776465e-06, "loss": 0.2978, "step": 895 }, { "epoch": 3.6360871768879877, "grad_norm": 0.2113943841412114, "learning_rate": 8.331711018202694e-06, "loss": 0.2864, "step": 896 }, { "epoch": 3.640141915864166, "grad_norm": 0.20715015285193783, "learning_rate": 8.285660113436104e-06, "loss": 0.2931, "step": 897 }, { "epoch": 3.6441966548403446, "grad_norm": 0.2043917350268456, "learning_rate": 8.239703554352527e-06, "loss": 0.2957, "step": 898 }, { "epoch": 3.648251393816523, "grad_norm": 0.19037666046633223, "learning_rate": 8.193841711079775e-06, "loss": 0.2783, "step": 899 }, { "epoch": 3.6523061327927016, "grad_norm": 0.20677672469983113, "learning_rate": 8.148074952982828e-06, "loss": 0.295, "step": 900 }, { "epoch": 3.65636087176888, "grad_norm": 0.1943156756797164, "learning_rate": 8.102403648660859e-06, "loss": 0.2948, "step": 901 }, { "epoch": 3.6604156107450585, "grad_norm": 0.19741086271405558, "learning_rate": 8.056828165944282e-06, "loss": 0.2913, "step": 902 }, { "epoch": 3.6644703497212365, "grad_norm": 0.1928007458736132, "learning_rate": 8.011348871891762e-06, "loss": 0.2856, "step": 903 }, { "epoch": 3.668525088697415, "grad_norm": 0.19079452621584028, "learning_rate": 7.965966132787287e-06, "loss": 0.2895, "step": 904 }, { "epoch": 3.6725798276735935, "grad_norm": 0.19516511288986674, "learning_rate": 7.920680314137189e-06, "loss": 0.2836, "step": 905 }, { "epoch": 3.676634566649772, "grad_norm": 0.20085377711071176, "learning_rate": 7.875491780667246e-06, "loss": 0.2877, "step": 906 }, { "epoch": 3.6806893056259504, "grad_norm": 0.21499494599756522, "learning_rate": 7.830400896319667e-06, "loss": 0.2916, "step": 907 }, { "epoch": 3.684744044602129, "grad_norm": 0.18748592290920887, "learning_rate": 7.785408024250259e-06, "loss": 0.2848, "step": 908 }, { "epoch": 3.6887987835783074, "grad_norm": 0.19864009505467262, "learning_rate": 7.74051352682542e-06, "loss": 0.2766, "step": 909 }, { "epoch": 3.6928535225544854, "grad_norm": 0.19145444060157296, "learning_rate": 7.695717765619257e-06, "loss": 0.2966, "step": 910 }, { "epoch": 3.696908261530664, "grad_norm": 0.20321033992621707, "learning_rate": 7.651021101410673e-06, "loss": 0.2992, "step": 911 }, { "epoch": 3.7009630005068423, "grad_norm": 0.20488870615665825, "learning_rate": 7.606423894180464e-06, "loss": 0.2861, "step": 912 }, { "epoch": 3.705017739483021, "grad_norm": 0.19193326036555286, "learning_rate": 7.56192650310839e-06, "loss": 0.2851, "step": 913 }, { "epoch": 3.7090724784591993, "grad_norm": 0.20177417544844975, "learning_rate": 7.517529286570349e-06, "loss": 0.2904, "step": 914 }, { "epoch": 3.7131272174353773, "grad_norm": 0.19604629678542201, "learning_rate": 7.473232602135387e-06, "loss": 0.295, "step": 915 }, { "epoch": 3.7171819564115562, "grad_norm": 0.20318050038598537, "learning_rate": 7.429036806562935e-06, "loss": 0.2853, "step": 916 }, { "epoch": 3.7212366953877343, "grad_norm": 0.1947514363344019, "learning_rate": 7.3849422557998455e-06, "loss": 0.2833, "step": 917 }, { "epoch": 3.7252914343639127, "grad_norm": 0.2013133391550272, "learning_rate": 7.340949304977567e-06, "loss": 0.2914, "step": 918 }, { "epoch": 3.729346173340091, "grad_norm": 0.1990012135368276, "learning_rate": 7.297058308409282e-06, "loss": 0.2778, "step": 919 }, { "epoch": 3.7334009123162697, "grad_norm": 0.20474998043662154, "learning_rate": 7.25326961958704e-06, "loss": 0.2741, "step": 920 }, { "epoch": 3.737455651292448, "grad_norm": 0.19598889222651866, "learning_rate": 7.209583591178921e-06, "loss": 0.2898, "step": 921 }, { "epoch": 3.741510390268626, "grad_norm": 0.19077951985088543, "learning_rate": 7.1660005750261925e-06, "loss": 0.2846, "step": 922 }, { "epoch": 3.745565129244805, "grad_norm": 0.1969385805380618, "learning_rate": 7.1225209221404765e-06, "loss": 0.289, "step": 923 }, { "epoch": 3.749619868220983, "grad_norm": 0.1903194474491913, "learning_rate": 7.079144982700909e-06, "loss": 0.2878, "step": 924 }, { "epoch": 3.7536746071971616, "grad_norm": 0.18245271164121174, "learning_rate": 7.0358731060513695e-06, "loss": 0.2816, "step": 925 }, { "epoch": 3.75772934617334, "grad_norm": 0.20203206400426488, "learning_rate": 6.99270564069757e-06, "loss": 0.2896, "step": 926 }, { "epoch": 3.7617840851495186, "grad_norm": 0.18865567426985286, "learning_rate": 6.949642934304375e-06, "loss": 0.2852, "step": 927 }, { "epoch": 3.765838824125697, "grad_norm": 0.20475346211887438, "learning_rate": 6.906685333692871e-06, "loss": 0.2872, "step": 928 }, { "epoch": 3.769893563101875, "grad_norm": 0.20934826665308667, "learning_rate": 6.86383318483769e-06, "loss": 0.2879, "step": 929 }, { "epoch": 3.773948302078054, "grad_norm": 2.690414812117868, "learning_rate": 6.821086832864139e-06, "loss": 0.3329, "step": 930 }, { "epoch": 3.778003041054232, "grad_norm": 0.2023831764738365, "learning_rate": 6.77844662204546e-06, "loss": 0.2864, "step": 931 }, { "epoch": 3.7820577800304105, "grad_norm": 0.1962249891193891, "learning_rate": 6.7359128958000455e-06, "loss": 0.2918, "step": 932 }, { "epoch": 3.786112519006589, "grad_norm": 0.20514154425781395, "learning_rate": 6.693485996688695e-06, "loss": 0.281, "step": 933 }, { "epoch": 3.7901672579827674, "grad_norm": 0.2003870205886511, "learning_rate": 6.651166266411801e-06, "loss": 0.292, "step": 934 }, { "epoch": 3.794221996958946, "grad_norm": 0.2099832277317987, "learning_rate": 6.6089540458066725e-06, "loss": 0.2996, "step": 935 }, { "epoch": 3.798276735935124, "grad_norm": 0.20881861580167743, "learning_rate": 6.566849674844711e-06, "loss": 0.2836, "step": 936 }, { "epoch": 3.802331474911303, "grad_norm": 0.19672574388102326, "learning_rate": 6.524853492628747e-06, "loss": 0.2786, "step": 937 }, { "epoch": 3.806386213887481, "grad_norm": 0.19838934581485307, "learning_rate": 6.4829658373902536e-06, "loss": 0.2945, "step": 938 }, { "epoch": 3.8104409528636594, "grad_norm": 0.2010821085695864, "learning_rate": 6.441187046486648e-06, "loss": 0.2703, "step": 939 }, { "epoch": 3.814495691839838, "grad_norm": 0.1809601731731134, "learning_rate": 6.399517456398567e-06, "loss": 0.2897, "step": 940 }, { "epoch": 3.8185504308160163, "grad_norm": 0.20288573110218783, "learning_rate": 6.357957402727164e-06, "loss": 0.2943, "step": 941 }, { "epoch": 3.822605169792195, "grad_norm": 0.19787432142322856, "learning_rate": 6.316507220191395e-06, "loss": 0.2811, "step": 942 }, { "epoch": 3.826659908768373, "grad_norm": 0.1927601591451861, "learning_rate": 6.275167242625331e-06, "loss": 0.2805, "step": 943 }, { "epoch": 3.8307146477445513, "grad_norm": 0.1950532039271898, "learning_rate": 6.233937802975471e-06, "loss": 0.29, "step": 944 }, { "epoch": 3.8347693867207298, "grad_norm": 0.21143410625275294, "learning_rate": 6.192819233298046e-06, "loss": 0.2839, "step": 945 }, { "epoch": 3.8388241256969082, "grad_norm": 0.17916045377236997, "learning_rate": 6.151811864756383e-06, "loss": 0.272, "step": 946 }, { "epoch": 3.8428788646730867, "grad_norm": 0.19417695064730034, "learning_rate": 6.1109160276181655e-06, "loss": 0.2947, "step": 947 }, { "epoch": 3.846933603649265, "grad_norm": 0.200466722508477, "learning_rate": 6.070132051252868e-06, "loss": 0.2769, "step": 948 }, { "epoch": 3.8509883426254437, "grad_norm": 0.19467436987914238, "learning_rate": 6.0294602641290034e-06, "loss": 0.2915, "step": 949 }, { "epoch": 3.8550430816016217, "grad_norm": 0.2064523716819283, "learning_rate": 5.988900993811575e-06, "loss": 0.2998, "step": 950 }, { "epoch": 3.8590978205778, "grad_norm": 0.2225581260458428, "learning_rate": 5.948454566959363e-06, "loss": 0.2891, "step": 951 }, { "epoch": 3.8631525595539786, "grad_norm": 0.1985498332166421, "learning_rate": 5.908121309322328e-06, "loss": 0.2871, "step": 952 }, { "epoch": 3.867207298530157, "grad_norm": 0.1978337635349083, "learning_rate": 5.867901545738976e-06, "loss": 0.2886, "step": 953 }, { "epoch": 3.8712620375063356, "grad_norm": 0.19036950265199676, "learning_rate": 5.827795600133774e-06, "loss": 0.2915, "step": 954 }, { "epoch": 3.875316776482514, "grad_norm": 0.19631255027457398, "learning_rate": 5.787803795514466e-06, "loss": 0.2909, "step": 955 }, { "epoch": 3.8793715154586925, "grad_norm": 0.19972434452728524, "learning_rate": 5.747926453969576e-06, "loss": 0.2866, "step": 956 }, { "epoch": 3.8834262544348706, "grad_norm": 0.19681697480503133, "learning_rate": 5.708163896665708e-06, "loss": 0.297, "step": 957 }, { "epoch": 3.887480993411049, "grad_norm": 0.1974329542184593, "learning_rate": 5.668516443845047e-06, "loss": 0.2837, "step": 958 }, { "epoch": 3.8915357323872275, "grad_norm": 0.18087418150311665, "learning_rate": 5.6289844148227225e-06, "loss": 0.2989, "step": 959 }, { "epoch": 3.895590471363406, "grad_norm": 0.18095472823403777, "learning_rate": 5.5895681279842615e-06, "loss": 0.281, "step": 960 }, { "epoch": 3.8996452103395844, "grad_norm": 0.18864999790855627, "learning_rate": 5.550267900783019e-06, "loss": 0.2831, "step": 961 }, { "epoch": 3.903699949315763, "grad_norm": 0.19694871130333552, "learning_rate": 5.511084049737623e-06, "loss": 0.2895, "step": 962 }, { "epoch": 3.9077546882919414, "grad_norm": 0.1939744168884727, "learning_rate": 5.4720168904294215e-06, "loss": 0.2909, "step": 963 }, { "epoch": 3.9118094272681194, "grad_norm": 0.19131132918380697, "learning_rate": 5.433066737499948e-06, "loss": 0.2897, "step": 964 }, { "epoch": 3.915864166244298, "grad_norm": 0.2035160466465672, "learning_rate": 5.394233904648376e-06, "loss": 0.2872, "step": 965 }, { "epoch": 3.9199189052204764, "grad_norm": 0.182505423345102, "learning_rate": 5.355518704628997e-06, "loss": 0.2834, "step": 966 }, { "epoch": 3.923973644196655, "grad_norm": 0.18865148351960265, "learning_rate": 5.316921449248731e-06, "loss": 0.2766, "step": 967 }, { "epoch": 3.9280283831728333, "grad_norm": 0.19204238004583296, "learning_rate": 5.278442449364538e-06, "loss": 0.2907, "step": 968 }, { "epoch": 3.932083122149012, "grad_norm": 0.21351754134710263, "learning_rate": 5.240082014881016e-06, "loss": 0.2949, "step": 969 }, { "epoch": 3.9361378611251903, "grad_norm": 0.19300722742104182, "learning_rate": 5.201840454747822e-06, "loss": 0.2909, "step": 970 }, { "epoch": 3.9401926001013683, "grad_norm": 0.18326834705417847, "learning_rate": 5.163718076957223e-06, "loss": 0.2788, "step": 971 }, { "epoch": 3.9442473390775468, "grad_norm": 0.19537913494764844, "learning_rate": 5.125715188541609e-06, "loss": 0.2954, "step": 972 }, { "epoch": 3.9483020780537252, "grad_norm": 0.19529271824550495, "learning_rate": 5.087832095571021e-06, "loss": 0.2948, "step": 973 }, { "epoch": 3.9523568170299037, "grad_norm": 0.18911327864278923, "learning_rate": 5.0500691031506766e-06, "loss": 0.2897, "step": 974 }, { "epoch": 3.956411556006082, "grad_norm": 0.1976513748112034, "learning_rate": 5.01242651541854e-06, "loss": 0.2934, "step": 975 }, { "epoch": 3.9604662949822607, "grad_norm": 0.18490524853055623, "learning_rate": 4.974904635542815e-06, "loss": 0.279, "step": 976 }, { "epoch": 3.964521033958439, "grad_norm": 0.18856652564761966, "learning_rate": 4.937503765719582e-06, "loss": 0.2881, "step": 977 }, { "epoch": 3.968575772934617, "grad_norm": 0.18958162910555576, "learning_rate": 4.900224207170299e-06, "loss": 0.2937, "step": 978 }, { "epoch": 3.9726305119107956, "grad_norm": 0.18844914419942507, "learning_rate": 4.8630662601394065e-06, "loss": 0.2886, "step": 979 }, { "epoch": 3.976685250886974, "grad_norm": 0.1815712496661697, "learning_rate": 4.8260302238918995e-06, "loss": 0.2813, "step": 980 }, { "epoch": 3.9807399898631526, "grad_norm": 0.1845441019060578, "learning_rate": 4.789116396710924e-06, "loss": 0.281, "step": 981 }, { "epoch": 3.984794728839331, "grad_norm": 0.17783711461592533, "learning_rate": 4.752325075895368e-06, "loss": 0.2807, "step": 982 }, { "epoch": 3.9888494678155095, "grad_norm": 0.18670569948480537, "learning_rate": 4.715656557757473e-06, "loss": 0.279, "step": 983 }, { "epoch": 3.992904206791688, "grad_norm": 0.1819228983204784, "learning_rate": 4.679111137620442e-06, "loss": 0.2781, "step": 984 }, { "epoch": 3.996958945767866, "grad_norm": 0.18795054233891606, "learning_rate": 4.6426891098160585e-06, "loss": 0.2903, "step": 985 }, { "epoch": 4.002027369488089, "grad_norm": 0.25611426785881797, "learning_rate": 4.6063907676823474e-06, "loss": 0.2726, "step": 986 }, { "epoch": 4.006082108464268, "grad_norm": 0.3009740784074706, "learning_rate": 4.570216403561141e-06, "loss": 0.2563, "step": 987 }, { "epoch": 4.010136847440446, "grad_norm": 0.2220685596383187, "learning_rate": 4.534166308795815e-06, "loss": 0.2601, "step": 988 }, { "epoch": 4.014191586416624, "grad_norm": 0.37818673968714783, "learning_rate": 4.498240773728859e-06, "loss": 0.2613, "step": 989 }, { "epoch": 4.018246325392803, "grad_norm": 0.33882778422981286, "learning_rate": 4.462440087699609e-06, "loss": 0.2482, "step": 990 }, { "epoch": 4.022301064368981, "grad_norm": 0.2512401004268022, "learning_rate": 4.426764539041861e-06, "loss": 0.2547, "step": 991 }, { "epoch": 4.02635580334516, "grad_norm": 0.3324896614732195, "learning_rate": 4.391214415081582e-06, "loss": 0.2472, "step": 992 }, { "epoch": 4.030410542321338, "grad_norm": 0.3354233353099227, "learning_rate": 4.355790002134579e-06, "loss": 0.2586, "step": 993 }, { "epoch": 4.034465281297517, "grad_norm": 0.22595889595555568, "learning_rate": 4.320491585504207e-06, "loss": 0.2466, "step": 994 }, { "epoch": 4.038520020273695, "grad_norm": 0.2308081499821183, "learning_rate": 4.2853194494790615e-06, "loss": 0.2583, "step": 995 }, { "epoch": 4.042574759249873, "grad_norm": 0.32807079804651174, "learning_rate": 4.250273877330691e-06, "loss": 0.2527, "step": 996 }, { "epoch": 4.046629498226052, "grad_norm": 0.28858210578671417, "learning_rate": 4.215355151311313e-06, "loss": 0.273, "step": 997 }, { "epoch": 4.05068423720223, "grad_norm": 0.21149542564133636, "learning_rate": 4.180563552651542e-06, "loss": 0.2557, "step": 998 }, { "epoch": 4.054738976178409, "grad_norm": 0.23338815803860508, "learning_rate": 4.145899361558147e-06, "loss": 0.2591, "step": 999 }, { "epoch": 4.058793715154587, "grad_norm": 0.28357771911471347, "learning_rate": 4.111362857211738e-06, "loss": 0.2572, "step": 1000 }, { "epoch": 4.062848454130766, "grad_norm": 0.23095203369354125, "learning_rate": 4.076954317764592e-06, "loss": 0.2524, "step": 1001 }, { "epoch": 4.066903193106944, "grad_norm": 0.216308088892441, "learning_rate": 4.042674020338335e-06, "loss": 0.259, "step": 1002 }, { "epoch": 4.070957932083122, "grad_norm": 0.24940401575861776, "learning_rate": 4.0085222410217835e-06, "loss": 0.2642, "step": 1003 }, { "epoch": 4.075012671059301, "grad_norm": 0.2520865489122057, "learning_rate": 3.974499254868674e-06, "loss": 0.2473, "step": 1004 }, { "epoch": 4.079067410035479, "grad_norm": 0.21939790266513742, "learning_rate": 3.940605335895451e-06, "loss": 0.2615, "step": 1005 }, { "epoch": 4.083122149011658, "grad_norm": 0.20290191414086048, "learning_rate": 3.90684075707908e-06, "loss": 0.2486, "step": 1006 }, { "epoch": 4.087176887987836, "grad_norm": 0.22517440131461885, "learning_rate": 3.8732057903548505e-06, "loss": 0.2545, "step": 1007 }, { "epoch": 4.0912316269640145, "grad_norm": 0.219420440504004, "learning_rate": 3.8397007066141375e-06, "loss": 0.2574, "step": 1008 }, { "epoch": 4.095286365940193, "grad_norm": 0.20275209134271466, "learning_rate": 3.806325775702304e-06, "loss": 0.2475, "step": 1009 }, { "epoch": 4.099341104916371, "grad_norm": 0.20199296510155496, "learning_rate": 3.773081266416434e-06, "loss": 0.2573, "step": 1010 }, { "epoch": 4.1033958438925495, "grad_norm": 0.2104784354140708, "learning_rate": 3.739967446503245e-06, "loss": 0.2588, "step": 1011 }, { "epoch": 4.1074505828687276, "grad_norm": 0.22248346194573435, "learning_rate": 3.706984582656894e-06, "loss": 0.258, "step": 1012 }, { "epoch": 4.1115053218449065, "grad_norm": 0.20851077091229103, "learning_rate": 3.6741329405168237e-06, "loss": 0.2562, "step": 1013 }, { "epoch": 4.1155600608210845, "grad_norm": 0.1958882681486163, "learning_rate": 3.641412784665648e-06, "loss": 0.2562, "step": 1014 }, { "epoch": 4.119614799797263, "grad_norm": 0.21562517074398682, "learning_rate": 3.608824378627005e-06, "loss": 0.2547, "step": 1015 }, { "epoch": 4.1236695387734414, "grad_norm": 0.19927856189029958, "learning_rate": 3.5763679848634337e-06, "loss": 0.2569, "step": 1016 }, { "epoch": 4.1277242777496195, "grad_norm": 0.18425837090239044, "learning_rate": 3.544043864774269e-06, "loss": 0.2438, "step": 1017 }, { "epoch": 4.131779016725798, "grad_norm": 0.20843553445148166, "learning_rate": 3.5118522786935282e-06, "loss": 0.2557, "step": 1018 }, { "epoch": 4.135833755701976, "grad_norm": 0.20654188862170156, "learning_rate": 3.479793485887819e-06, "loss": 0.2506, "step": 1019 }, { "epoch": 4.139888494678155, "grad_norm": 0.18997365595535873, "learning_rate": 3.4478677445542653e-06, "loss": 0.2608, "step": 1020 }, { "epoch": 4.143943233654333, "grad_norm": 0.18401833747820887, "learning_rate": 3.4160753118183767e-06, "loss": 0.2592, "step": 1021 }, { "epoch": 4.147997972630512, "grad_norm": 0.18939333943591466, "learning_rate": 3.3844164437320527e-06, "loss": 0.2491, "step": 1022 }, { "epoch": 4.15205271160669, "grad_norm": 0.1963989230108815, "learning_rate": 3.3528913952714558e-06, "loss": 0.2569, "step": 1023 }, { "epoch": 4.156107450582868, "grad_norm": 0.18791392793834086, "learning_rate": 3.321500420335e-06, "loss": 0.254, "step": 1024 }, { "epoch": 4.160162189559047, "grad_norm": 0.17757277007698027, "learning_rate": 3.290243771741275e-06, "loss": 0.2452, "step": 1025 }, { "epoch": 4.164216928535225, "grad_norm": 0.19347309932301202, "learning_rate": 3.2591217012270325e-06, "loss": 0.2481, "step": 1026 }, { "epoch": 4.168271667511404, "grad_norm": 0.19255532213199955, "learning_rate": 3.228134459445149e-06, "loss": 0.249, "step": 1027 }, { "epoch": 4.172326406487582, "grad_norm": 0.19682484435891645, "learning_rate": 3.1972822959626205e-06, "loss": 0.2505, "step": 1028 }, { "epoch": 4.176381145463761, "grad_norm": 0.1847304263952064, "learning_rate": 3.166565459258513e-06, "loss": 0.2569, "step": 1029 }, { "epoch": 4.180435884439939, "grad_norm": 0.1779070396300901, "learning_rate": 3.1359841967220193e-06, "loss": 0.2491, "step": 1030 }, { "epoch": 4.184490623416117, "grad_norm": 0.19241550870330695, "learning_rate": 3.105538754650419e-06, "loss": 0.2464, "step": 1031 }, { "epoch": 4.188545362392296, "grad_norm": 0.19742983726212854, "learning_rate": 3.07522937824712e-06, "loss": 0.2544, "step": 1032 }, { "epoch": 4.192600101368474, "grad_norm": 0.1869274377527996, "learning_rate": 3.0450563116196697e-06, "loss": 0.2578, "step": 1033 }, { "epoch": 4.196654840344653, "grad_norm": 0.1880009397745851, "learning_rate": 3.0150197977778008e-06, "loss": 0.2518, "step": 1034 }, { "epoch": 4.200709579320831, "grad_norm": 0.18668104688306322, "learning_rate": 2.985120078631465e-06, "loss": 0.2528, "step": 1035 }, { "epoch": 4.20476431829701, "grad_norm": 0.1863767432393886, "learning_rate": 2.9553573949888893e-06, "loss": 0.2481, "step": 1036 }, { "epoch": 4.208819057273188, "grad_norm": 0.1840276628918648, "learning_rate": 2.9257319865546384e-06, "loss": 0.2513, "step": 1037 }, { "epoch": 4.212873796249366, "grad_norm": 0.19525984576463282, "learning_rate": 2.896244091927678e-06, "loss": 0.25, "step": 1038 }, { "epoch": 4.216928535225545, "grad_norm": 0.1842052329649811, "learning_rate": 2.8668939485994584e-06, "loss": 0.251, "step": 1039 }, { "epoch": 4.220983274201723, "grad_norm": 0.18983098392093753, "learning_rate": 2.837681792951994e-06, "loss": 0.2332, "step": 1040 }, { "epoch": 4.225038013177902, "grad_norm": 0.18161211016419382, "learning_rate": 2.808607860255981e-06, "loss": 0.2621, "step": 1041 }, { "epoch": 4.22909275215408, "grad_norm": 0.18352211206286106, "learning_rate": 2.7796723846688634e-06, "loss": 0.2655, "step": 1042 }, { "epoch": 4.233147491130259, "grad_norm": 0.17517438842152963, "learning_rate": 2.7508755992329937e-06, "loss": 0.2401, "step": 1043 }, { "epoch": 4.237202230106437, "grad_norm": 0.1815140482763408, "learning_rate": 2.722217735873718e-06, "loss": 0.2612, "step": 1044 }, { "epoch": 4.241256969082615, "grad_norm": 0.18464277856884287, "learning_rate": 2.6936990253975315e-06, "loss": 0.2524, "step": 1045 }, { "epoch": 4.245311708058794, "grad_norm": 0.1772524712492246, "learning_rate": 2.665319697490205e-06, "loss": 0.2571, "step": 1046 }, { "epoch": 4.249366447034972, "grad_norm": 0.17972521572321065, "learning_rate": 2.637079980714945e-06, "loss": 0.2436, "step": 1047 }, { "epoch": 4.253421186011151, "grad_norm": 0.17925237174999503, "learning_rate": 2.6089801025105453e-06, "loss": 0.2523, "step": 1048 }, { "epoch": 4.257475924987329, "grad_norm": 0.18166267833734925, "learning_rate": 2.581020289189571e-06, "loss": 0.2543, "step": 1049 }, { "epoch": 4.261530663963507, "grad_norm": 0.1759588335700954, "learning_rate": 2.553200765936501e-06, "loss": 0.2379, "step": 1050 }, { "epoch": 4.265585402939686, "grad_norm": 0.17752241762323948, "learning_rate": 2.525521756805962e-06, "loss": 0.2625, "step": 1051 }, { "epoch": 4.269640141915864, "grad_norm": 0.17656471372533553, "learning_rate": 2.497983484720885e-06, "loss": 0.2475, "step": 1052 }, { "epoch": 4.273694880892043, "grad_norm": 0.18015386279469092, "learning_rate": 2.470586171470728e-06, "loss": 0.2466, "step": 1053 }, { "epoch": 4.277749619868221, "grad_norm": 0.18169664940799468, "learning_rate": 2.4433300377096836e-06, "loss": 0.263, "step": 1054 }, { "epoch": 4.2818043588444, "grad_norm": 0.17701639966899047, "learning_rate": 2.4162153029549073e-06, "loss": 0.253, "step": 1055 }, { "epoch": 4.285859097820578, "grad_norm": 0.19324038107684985, "learning_rate": 2.3892421855847458e-06, "loss": 0.2396, "step": 1056 }, { "epoch": 4.289913836796757, "grad_norm": 0.17698659107819212, "learning_rate": 2.362410902836978e-06, "loss": 0.2549, "step": 1057 }, { "epoch": 4.293968575772935, "grad_norm": 0.17935458845344954, "learning_rate": 2.3357216708070653e-06, "loss": 0.2491, "step": 1058 }, { "epoch": 4.298023314749113, "grad_norm": 0.178713274433982, "learning_rate": 2.309174704446411e-06, "loss": 0.2605, "step": 1059 }, { "epoch": 4.302078053725292, "grad_norm": 0.1776904794300703, "learning_rate": 2.2827702175606437e-06, "loss": 0.2463, "step": 1060 }, { "epoch": 4.30613279270147, "grad_norm": 0.17914119747553423, "learning_rate": 2.256508422807855e-06, "loss": 0.258, "step": 1061 }, { "epoch": 4.310187531677649, "grad_norm": 0.17866383482903628, "learning_rate": 2.230389531696946e-06, "loss": 0.2516, "step": 1062 }, { "epoch": 4.314242270653827, "grad_norm": 0.16538142795067087, "learning_rate": 2.204413754585857e-06, "loss": 0.2423, "step": 1063 }, { "epoch": 4.318297009630005, "grad_norm": 0.18220468898776407, "learning_rate": 2.1785813006799406e-06, "loss": 0.2366, "step": 1064 }, { "epoch": 4.3223517486061835, "grad_norm": 0.17546018489695162, "learning_rate": 2.1528923780302224e-06, "loss": 0.2456, "step": 1065 }, { "epoch": 4.326406487582362, "grad_norm": 0.1740824900335368, "learning_rate": 2.127347193531757e-06, "loss": 0.2448, "step": 1066 }, { "epoch": 4.3304612265585405, "grad_norm": 0.17415036654000435, "learning_rate": 2.101945952921942e-06, "loss": 0.2438, "step": 1067 }, { "epoch": 4.3345159655347185, "grad_norm": 0.16898632982789935, "learning_rate": 2.0766888607788906e-06, "loss": 0.2536, "step": 1068 }, { "epoch": 4.338570704510897, "grad_norm": 0.169778601065716, "learning_rate": 2.0515761205197337e-06, "loss": 0.2619, "step": 1069 }, { "epoch": 4.3426254434870755, "grad_norm": 0.18287697566336356, "learning_rate": 2.0266079343990453e-06, "loss": 0.2478, "step": 1070 }, { "epoch": 4.346680182463254, "grad_norm": 0.1713387806790273, "learning_rate": 2.0017845035071494e-06, "loss": 0.261, "step": 1071 }, { "epoch": 4.350734921439432, "grad_norm": 0.17590717321598467, "learning_rate": 1.9771060277685537e-06, "loss": 0.2571, "step": 1072 }, { "epoch": 4.35478966041561, "grad_norm": 0.1789381577267048, "learning_rate": 1.95257270594031e-06, "loss": 0.2536, "step": 1073 }, { "epoch": 4.358844399391789, "grad_norm": 0.1771624527208628, "learning_rate": 1.9281847356104188e-06, "loss": 0.25, "step": 1074 }, { "epoch": 4.362899138367967, "grad_norm": 0.1766301521470837, "learning_rate": 1.9039423131962365e-06, "loss": 0.2516, "step": 1075 }, { "epoch": 4.366953877344146, "grad_norm": 0.17249564497956757, "learning_rate": 1.8798456339429027e-06, "loss": 0.2512, "step": 1076 }, { "epoch": 4.371008616320324, "grad_norm": 0.17530208114697401, "learning_rate": 1.8558948919217612e-06, "loss": 0.257, "step": 1077 }, { "epoch": 4.375063355296502, "grad_norm": 0.17433065715138585, "learning_rate": 1.8320902800287954e-06, "loss": 0.2504, "step": 1078 }, { "epoch": 4.379118094272681, "grad_norm": 0.17702279493051556, "learning_rate": 1.8084319899830726e-06, "loss": 0.2539, "step": 1079 }, { "epoch": 4.383172833248859, "grad_norm": 0.17012227119709558, "learning_rate": 1.7849202123252097e-06, "loss": 0.2587, "step": 1080 }, { "epoch": 4.387227572225038, "grad_norm": 0.16782352416302623, "learning_rate": 1.7615551364158401e-06, "loss": 0.2551, "step": 1081 }, { "epoch": 4.391282311201216, "grad_norm": 0.17709290597334804, "learning_rate": 1.738336950434061e-06, "loss": 0.2516, "step": 1082 }, { "epoch": 4.395337050177395, "grad_norm": 0.17480467023058002, "learning_rate": 1.715265841375957e-06, "loss": 0.2642, "step": 1083 }, { "epoch": 4.399391789153573, "grad_norm": 0.17884248341342662, "learning_rate": 1.6923419950530684e-06, "loss": 0.2503, "step": 1084 }, { "epoch": 4.403446528129751, "grad_norm": 0.1738466590542009, "learning_rate": 1.6695655960909008e-06, "loss": 0.2576, "step": 1085 }, { "epoch": 4.40750126710593, "grad_norm": 0.16545289876583502, "learning_rate": 1.646936827927441e-06, "loss": 0.2503, "step": 1086 }, { "epoch": 4.411556006082108, "grad_norm": 0.1688791188575171, "learning_rate": 1.6244558728116766e-06, "loss": 0.2541, "step": 1087 }, { "epoch": 4.415610745058287, "grad_norm": 0.18265532447713828, "learning_rate": 1.6021229118021265e-06, "loss": 0.2497, "step": 1088 }, { "epoch": 4.419665484034465, "grad_norm": 0.17153840271699716, "learning_rate": 1.5799381247653967e-06, "loss": 0.2605, "step": 1089 }, { "epoch": 4.423720223010644, "grad_norm": 0.17605100775717153, "learning_rate": 1.5579016903747013e-06, "loss": 0.2412, "step": 1090 }, { "epoch": 4.427774961986822, "grad_norm": 0.16588455862743817, "learning_rate": 1.5360137861084656e-06, "loss": 0.2537, "step": 1091 }, { "epoch": 4.431829700963, "grad_norm": 0.17034099921782977, "learning_rate": 1.5142745882488475e-06, "loss": 0.2591, "step": 1092 }, { "epoch": 4.435884439939179, "grad_norm": 0.16846852341526058, "learning_rate": 1.4926842718803691e-06, "loss": 0.2443, "step": 1093 }, { "epoch": 4.439939178915357, "grad_norm": 0.175265273025731, "learning_rate": 1.4712430108884657e-06, "loss": 0.2527, "step": 1094 }, { "epoch": 4.443993917891536, "grad_norm": 0.17133282080278295, "learning_rate": 1.4499509779581078e-06, "loss": 0.2596, "step": 1095 }, { "epoch": 4.448048656867714, "grad_norm": 0.1674211247708412, "learning_rate": 1.4288083445723988e-06, "loss": 0.2566, "step": 1096 }, { "epoch": 4.452103395843893, "grad_norm": 0.17958830520541688, "learning_rate": 1.4078152810112045e-06, "loss": 0.2492, "step": 1097 }, { "epoch": 4.456158134820071, "grad_norm": 0.17569148707223403, "learning_rate": 1.3869719563497697e-06, "loss": 0.2549, "step": 1098 }, { "epoch": 4.460212873796249, "grad_norm": 0.1710113005955467, "learning_rate": 1.3662785384573663e-06, "loss": 0.2518, "step": 1099 }, { "epoch": 4.464267612772428, "grad_norm": 0.17425963967824554, "learning_rate": 1.3457351939959383e-06, "loss": 0.2534, "step": 1100 }, { "epoch": 4.468322351748606, "grad_norm": 0.17383301006485435, "learning_rate": 1.3253420884187551e-06, "loss": 0.2602, "step": 1101 }, { "epoch": 4.472377090724785, "grad_norm": 0.16734482608615803, "learning_rate": 1.3050993859690953e-06, "loss": 0.2567, "step": 1102 }, { "epoch": 4.476431829700963, "grad_norm": 0.17281941803873102, "learning_rate": 1.2850072496788869e-06, "loss": 0.2422, "step": 1103 }, { "epoch": 4.480486568677142, "grad_norm": 0.1715766072317696, "learning_rate": 1.2650658413674434e-06, "loss": 0.2578, "step": 1104 }, { "epoch": 4.48454130765332, "grad_norm": 0.17468508668157104, "learning_rate": 1.2452753216401226e-06, "loss": 0.2455, "step": 1105 }, { "epoch": 4.488596046629498, "grad_norm": 0.16897632920154224, "learning_rate": 1.2256358498870503e-06, "loss": 0.244, "step": 1106 }, { "epoch": 4.492650785605677, "grad_norm": 0.1769012029409341, "learning_rate": 1.2061475842818337e-06, "loss": 0.2438, "step": 1107 }, { "epoch": 4.496705524581855, "grad_norm": 0.1652674422222274, "learning_rate": 1.1868106817802816e-06, "loss": 0.2563, "step": 1108 }, { "epoch": 4.500760263558034, "grad_norm": 0.1723341053241152, "learning_rate": 1.1676252981191482e-06, "loss": 0.2544, "step": 1109 }, { "epoch": 4.504815002534212, "grad_norm": 0.16880699150440717, "learning_rate": 1.1485915878148823e-06, "loss": 0.2489, "step": 1110 }, { "epoch": 4.50886974151039, "grad_norm": 0.17508393559955296, "learning_rate": 1.1297097041623584e-06, "loss": 0.2492, "step": 1111 }, { "epoch": 4.512924480486569, "grad_norm": 0.17103462863974223, "learning_rate": 1.1109797992336847e-06, "loss": 0.257, "step": 1112 }, { "epoch": 4.516979219462747, "grad_norm": 0.17243328355634502, "learning_rate": 1.092402023876933e-06, "loss": 0.242, "step": 1113 }, { "epoch": 4.521033958438926, "grad_norm": 0.17874932217952627, "learning_rate": 1.0739765277149527e-06, "loss": 0.256, "step": 1114 }, { "epoch": 4.525088697415104, "grad_norm": 0.1687589575907724, "learning_rate": 1.0557034591441596e-06, "loss": 0.253, "step": 1115 }, { "epoch": 4.529143436391283, "grad_norm": 0.16865840386491973, "learning_rate": 1.0375829653333324e-06, "loss": 0.2493, "step": 1116 }, { "epoch": 4.533198175367461, "grad_norm": 0.17173202921401556, "learning_rate": 1.0196151922224385e-06, "loss": 0.2605, "step": 1117 }, { "epoch": 4.5372529143436395, "grad_norm": 0.17424072149412476, "learning_rate": 1.0018002845214526e-06, "loss": 0.2508, "step": 1118 }, { "epoch": 4.541307653319818, "grad_norm": 0.2954404606251542, "learning_rate": 9.841383857091947e-07, "loss": 0.2574, "step": 1119 }, { "epoch": 4.545362392295996, "grad_norm": 0.166246858948724, "learning_rate": 9.666296380321616e-07, "loss": 0.2581, "step": 1120 }, { "epoch": 4.5494171312721745, "grad_norm": 0.16843525290963585, "learning_rate": 9.492741825034124e-07, "loss": 0.2513, "step": 1121 }, { "epoch": 4.5534718702483525, "grad_norm": 0.18110289729694456, "learning_rate": 9.320721589013892e-07, "loss": 0.259, "step": 1122 }, { "epoch": 4.5575266092245315, "grad_norm": 0.18398542388139213, "learning_rate": 9.150237057688339e-07, "loss": 0.2534, "step": 1123 }, { "epoch": 4.5615813482007095, "grad_norm": 0.17270261047121901, "learning_rate": 8.981289604116328e-07, "loss": 0.2497, "step": 1124 }, { "epoch": 4.5656360871768875, "grad_norm": 0.1681621156615096, "learning_rate": 8.813880588977542e-07, "loss": 0.2491, "step": 1125 }, { "epoch": 4.569690826153066, "grad_norm": 0.16375764179935567, "learning_rate": 8.648011360561126e-07, "loss": 0.2448, "step": 1126 }, { "epoch": 4.5737455651292445, "grad_norm": 0.17073726852501087, "learning_rate": 8.483683254755037e-07, "loss": 0.2555, "step": 1127 }, { "epoch": 4.577800304105423, "grad_norm": 0.17526627492363367, "learning_rate": 8.320897595035227e-07, "loss": 0.2414, "step": 1128 }, { "epoch": 4.581855043081601, "grad_norm": 0.17122543460352002, "learning_rate": 8.159655692455093e-07, "loss": 0.2576, "step": 1129 }, { "epoch": 4.58590978205778, "grad_norm": 0.1707586828140403, "learning_rate": 7.999958845634648e-07, "loss": 0.2516, "step": 1130 }, { "epoch": 4.589964521033958, "grad_norm": 0.17590847363507778, "learning_rate": 7.841808340750478e-07, "loss": 0.2499, "step": 1131 }, { "epoch": 4.594019260010137, "grad_norm": 0.1687656793547117, "learning_rate": 7.685205451524869e-07, "loss": 0.2538, "step": 1132 }, { "epoch": 4.598073998986315, "grad_norm": 0.17047474360683673, "learning_rate": 7.530151439216027e-07, "loss": 0.2571, "step": 1133 }, { "epoch": 4.602128737962493, "grad_norm": 0.1709690439376052, "learning_rate": 7.376647552607675e-07, "loss": 0.2557, "step": 1134 }, { "epoch": 4.606183476938672, "grad_norm": 0.17504337448842014, "learning_rate": 7.224695027998963e-07, "loss": 0.236, "step": 1135 }, { "epoch": 4.61023821591485, "grad_norm": 0.17240440071070331, "learning_rate": 7.07429508919466e-07, "loss": 0.2561, "step": 1136 }, { "epoch": 4.614292954891029, "grad_norm": 0.17248629560794781, "learning_rate": 6.925448947495206e-07, "loss": 0.2448, "step": 1137 }, { "epoch": 4.618347693867207, "grad_norm": 0.16960853964063932, "learning_rate": 6.778157801686936e-07, "loss": 0.2463, "step": 1138 }, { "epoch": 4.622402432843385, "grad_norm": 0.16719702116079962, "learning_rate": 6.632422838032515e-07, "loss": 0.2546, "step": 1139 }, { "epoch": 4.626457171819564, "grad_norm": 0.17166052005878968, "learning_rate": 6.488245230261281e-07, "loss": 0.2442, "step": 1140 }, { "epoch": 4.630511910795742, "grad_norm": 0.16558649291931105, "learning_rate": 6.345626139559868e-07, "loss": 0.2443, "step": 1141 }, { "epoch": 4.634566649771921, "grad_norm": 0.16787417108247757, "learning_rate": 6.204566714562866e-07, "loss": 0.2557, "step": 1142 }, { "epoch": 4.638621388748099, "grad_norm": 0.1701030155904384, "learning_rate": 6.06506809134344e-07, "loss": 0.2627, "step": 1143 }, { "epoch": 4.642676127724278, "grad_norm": 0.16606071518200743, "learning_rate": 5.927131393404373e-07, "loss": 0.2534, "step": 1144 }, { "epoch": 4.646730866700456, "grad_norm": 0.16488393160850992, "learning_rate": 5.790757731668817e-07, "loss": 0.2438, "step": 1145 }, { "epoch": 4.650785605676635, "grad_norm": 0.17241123819856988, "learning_rate": 5.655948204471507e-07, "loss": 0.2432, "step": 1146 }, { "epoch": 4.654840344652813, "grad_norm": 0.17552497841818834, "learning_rate": 5.522703897549875e-07, "loss": 0.2535, "step": 1147 }, { "epoch": 4.658895083628991, "grad_norm": 0.1745218917483895, "learning_rate": 5.391025884035239e-07, "loss": 0.2513, "step": 1148 }, { "epoch": 4.66294982260517, "grad_norm": 0.17213600658750738, "learning_rate": 5.260915224444207e-07, "loss": 0.2478, "step": 1149 }, { "epoch": 4.667004561581348, "grad_norm": 0.1675142416139678, "learning_rate": 5.132372966670129e-07, "loss": 0.2656, "step": 1150 }, { "epoch": 4.671059300557527, "grad_norm": 0.17583299139186337, "learning_rate": 5.005400145974704e-07, "loss": 0.25, "step": 1151 }, { "epoch": 4.675114039533705, "grad_norm": 0.17565754053549767, "learning_rate": 4.879997784979562e-07, "loss": 0.2518, "step": 1152 }, { "epoch": 4.679168778509883, "grad_norm": 0.17142088811329584, "learning_rate": 4.7561668936580984e-07, "loss": 0.2502, "step": 1153 }, { "epoch": 4.683223517486062, "grad_norm": 0.170515116339513, "learning_rate": 4.6339084693272306e-07, "loss": 0.2467, "step": 1154 }, { "epoch": 4.68727825646224, "grad_norm": 0.16849792447303424, "learning_rate": 4.5132234966395847e-07, "loss": 0.2453, "step": 1155 }, { "epoch": 4.691332995438419, "grad_norm": 0.6555987205593216, "learning_rate": 4.3941129475752795e-07, "loss": 0.2863, "step": 1156 }, { "epoch": 4.695387734414597, "grad_norm": 0.1662846334803649, "learning_rate": 4.27657778143431e-07, "loss": 0.2478, "step": 1157 }, { "epoch": 4.699442473390776, "grad_norm": 0.17153820529128797, "learning_rate": 4.1606189448287757e-07, "loss": 0.2567, "step": 1158 }, { "epoch": 4.703497212366954, "grad_norm": 0.1668792433997687, "learning_rate": 4.046237371675177e-07, "loss": 0.2378, "step": 1159 }, { "epoch": 4.707551951343133, "grad_norm": 0.1616781070797042, "learning_rate": 3.9334339831869963e-07, "loss": 0.2442, "step": 1160 }, { "epoch": 4.711606690319311, "grad_norm": 0.1710792220874379, "learning_rate": 3.8222096878671955e-07, "loss": 0.2647, "step": 1161 }, { "epoch": 4.715661429295489, "grad_norm": 0.16771977433340546, "learning_rate": 3.7125653815009545e-07, "loss": 0.2577, "step": 1162 }, { "epoch": 4.719716168271668, "grad_norm": 0.17269424174474968, "learning_rate": 3.6045019471484974e-07, "loss": 0.2501, "step": 1163 }, { "epoch": 4.723770907247846, "grad_norm": 0.1687447081391345, "learning_rate": 3.498020255137813e-07, "loss": 0.2573, "step": 1164 }, { "epoch": 4.727825646224025, "grad_norm": 0.45593324973687643, "learning_rate": 3.393121163057811e-07, "loss": 0.2635, "step": 1165 }, { "epoch": 4.731880385200203, "grad_norm": 0.1662412437246564, "learning_rate": 3.289805515751399e-07, "loss": 0.2594, "step": 1166 }, { "epoch": 4.735935124176381, "grad_norm": 0.16718534079097605, "learning_rate": 3.188074145308573e-07, "loss": 0.2453, "step": 1167 }, { "epoch": 4.73998986315256, "grad_norm": 0.16753884625995394, "learning_rate": 3.087927871059804e-07, "loss": 0.2468, "step": 1168 }, { "epoch": 4.744044602128738, "grad_norm": 0.1710143111766643, "learning_rate": 2.989367499569418e-07, "loss": 0.254, "step": 1169 }, { "epoch": 4.748099341104917, "grad_norm": 0.16693147822000307, "learning_rate": 2.8923938246290917e-07, "loss": 0.2638, "step": 1170 }, { "epoch": 4.752154080081095, "grad_norm": 0.1702489124481913, "learning_rate": 2.7970076272514804e-07, "loss": 0.255, "step": 1171 }, { "epoch": 4.7562088190572736, "grad_norm": 0.17021476274370656, "learning_rate": 2.703209675663887e-07, "loss": 0.2502, "step": 1172 }, { "epoch": 4.760263558033452, "grad_norm": 0.1677806040339345, "learning_rate": 2.6110007253021374e-07, "loss": 0.2571, "step": 1173 }, { "epoch": 4.7643182970096305, "grad_norm": 0.16981330485304907, "learning_rate": 2.520381518804471e-07, "loss": 0.2416, "step": 1174 }, { "epoch": 4.7683730359858085, "grad_norm": 0.16634426567122834, "learning_rate": 2.4313527860054585e-07, "loss": 0.2515, "step": 1175 }, { "epoch": 4.772427774961987, "grad_norm": 0.17505053282218144, "learning_rate": 2.343915243930317e-07, "loss": 0.2541, "step": 1176 }, { "epoch": 4.7764825139381655, "grad_norm": 0.1655539886256611, "learning_rate": 2.2580695967889367e-07, "loss": 0.2493, "step": 1177 }, { "epoch": 4.7805372529143435, "grad_norm": 0.16413143513725126, "learning_rate": 2.1738165359704189e-07, "loss": 0.253, "step": 1178 }, { "epoch": 4.784591991890522, "grad_norm": 0.1703652128302836, "learning_rate": 2.0911567400373257e-07, "loss": 0.2449, "step": 1179 }, { "epoch": 4.7886467308667005, "grad_norm": 0.16519840721880963, "learning_rate": 2.0100908747202607e-07, "loss": 0.2625, "step": 1180 }, { "epoch": 4.7927014698428785, "grad_norm": 0.17742541758394886, "learning_rate": 1.9306195929125638e-07, "loss": 0.2519, "step": 1181 }, { "epoch": 4.796756208819057, "grad_norm": 0.159335085427381, "learning_rate": 1.8527435346650247e-07, "loss": 0.2525, "step": 1182 }, { "epoch": 4.800810947795235, "grad_norm": 0.16526297675042562, "learning_rate": 1.7764633271807108e-07, "loss": 0.256, "step": 1183 }, { "epoch": 4.804865686771414, "grad_norm": 0.170518741466379, "learning_rate": 1.7017795848099262e-07, "loss": 0.2435, "step": 1184 }, { "epoch": 4.808920425747592, "grad_norm": 0.16051696376179156, "learning_rate": 1.6286929090452596e-07, "loss": 0.2507, "step": 1185 }, { "epoch": 4.812975164723771, "grad_norm": 0.16342894703219665, "learning_rate": 1.557203888516745e-07, "loss": 0.25, "step": 1186 }, { "epoch": 4.817029903699949, "grad_norm": 0.1620661484084637, "learning_rate": 1.487313098987131e-07, "loss": 0.2471, "step": 1187 }, { "epoch": 4.821084642676127, "grad_norm": 0.16945588818262158, "learning_rate": 1.4190211033472402e-07, "loss": 0.2606, "step": 1188 }, { "epoch": 4.825139381652306, "grad_norm": 0.16315240105886247, "learning_rate": 1.3523284516113955e-07, "loss": 0.255, "step": 1189 }, { "epoch": 4.829194120628484, "grad_norm": 0.17148724559860798, "learning_rate": 1.2872356809130682e-07, "loss": 0.2475, "step": 1190 }, { "epoch": 4.833248859604663, "grad_norm": 0.16704046253285335, "learning_rate": 1.2237433155004807e-07, "loss": 0.2609, "step": 1191 }, { "epoch": 4.837303598580841, "grad_norm": 0.16601899879726528, "learning_rate": 1.1618518667323886e-07, "loss": 0.2526, "step": 1192 }, { "epoch": 4.84135833755702, "grad_norm": 0.16539918606290796, "learning_rate": 1.1015618330740385e-07, "loss": 0.2563, "step": 1193 }, { "epoch": 4.845413076533198, "grad_norm": 0.16930628586850244, "learning_rate": 1.042873700093061e-07, "loss": 0.2493, "step": 1194 }, { "epoch": 4.849467815509376, "grad_norm": 0.17703313971733867, "learning_rate": 9.857879404556291e-08, "loss": 0.251, "step": 1195 }, { "epoch": 4.853522554485555, "grad_norm": 0.16508770525676006, "learning_rate": 9.303050139225722e-08, "loss": 0.2439, "step": 1196 }, { "epoch": 4.857577293461733, "grad_norm": 0.17095500155755156, "learning_rate": 8.76425367345779e-08, "loss": 0.2566, "step": 1197 }, { "epoch": 4.861632032437912, "grad_norm": 0.1675642619299692, "learning_rate": 8.241494346644897e-08, "loss": 0.2455, "step": 1198 }, { "epoch": 4.86568677141409, "grad_norm": 0.16491262920896474, "learning_rate": 7.734776369019204e-08, "loss": 0.2639, "step": 1199 }, { "epoch": 4.869741510390268, "grad_norm": 0.1622511153314926, "learning_rate": 7.244103821617332e-08, "loss": 0.238, "step": 1200 }, { "epoch": 4.873796249366447, "grad_norm": 0.1670227896357684, "learning_rate": 6.769480656248606e-08, "loss": 0.2546, "step": 1201 }, { "epoch": 4.877850988342625, "grad_norm": 0.1618542414231665, "learning_rate": 6.310910695462635e-08, "loss": 0.2537, "step": 1202 }, { "epoch": 4.881905727318804, "grad_norm": 0.17353064894155007, "learning_rate": 5.8683976325191185e-08, "loss": 0.252, "step": 1203 }, { "epoch": 4.885960466294982, "grad_norm": 0.16593237553024018, "learning_rate": 5.4419450313571984e-08, "loss": 0.2499, "step": 1204 }, { "epoch": 4.890015205271161, "grad_norm": 0.16217599211566242, "learning_rate": 5.031556326567488e-08, "loss": 0.2584, "step": 1205 }, { "epoch": 4.894069944247339, "grad_norm": 0.1649736406904438, "learning_rate": 4.637234823364312e-08, "loss": 0.2514, "step": 1206 }, { "epoch": 4.898124683223518, "grad_norm": 0.16887289202506833, "learning_rate": 4.258983697558838e-08, "loss": 0.2559, "step": 1207 }, { "epoch": 4.902179422199696, "grad_norm": 0.16133216292473418, "learning_rate": 3.896805995533548e-08, "loss": 0.2588, "step": 1208 }, { "epoch": 4.906234161175874, "grad_norm": 0.1615936603901022, "learning_rate": 3.550704634218028e-08, "loss": 0.2532, "step": 1209 }, { "epoch": 4.910288900152053, "grad_norm": 0.16303393283520354, "learning_rate": 3.2206824010647676e-08, "loss": 0.2545, "step": 1210 }, { "epoch": 4.914343639128231, "grad_norm": 0.16945282352350352, "learning_rate": 2.9067419540278476e-08, "loss": 0.264, "step": 1211 }, { "epoch": 4.91839837810441, "grad_norm": 0.16890334544091284, "learning_rate": 2.6088858215400638e-08, "loss": 0.2433, "step": 1212 }, { "epoch": 4.922453117080588, "grad_norm": 0.1646612082639841, "learning_rate": 2.3271164024940564e-08, "loss": 0.2506, "step": 1213 }, { "epoch": 4.926507856056766, "grad_norm": 0.17006094104723612, "learning_rate": 2.061435966221881e-08, "loss": 0.2539, "step": 1214 }, { "epoch": 4.930562595032945, "grad_norm": 0.17289053251150838, "learning_rate": 1.811846652477245e-08, "loss": 0.2457, "step": 1215 }, { "epoch": 4.934617334009123, "grad_norm": 0.17568735053693194, "learning_rate": 1.5783504714184106e-08, "loss": 0.2448, "step": 1216 }, { "epoch": 4.938672072985302, "grad_norm": 0.16599084287431357, "learning_rate": 1.360949303591097e-08, "loss": 0.2549, "step": 1217 }, { "epoch": 4.94272681196148, "grad_norm": 0.1641086046269747, "learning_rate": 1.1596448999144916e-08, "loss": 0.2547, "step": 1218 }, { "epoch": 4.946781550937659, "grad_norm": 0.1625368803545357, "learning_rate": 9.744388816668172e-09, "loss": 0.2468, "step": 1219 }, { "epoch": 4.950836289913837, "grad_norm": 0.16985069448322035, "learning_rate": 8.05332740472009e-09, "loss": 0.2683, "step": 1220 }, { "epoch": 4.954891028890016, "grad_norm": 0.1764360184700717, "learning_rate": 6.523278382872811e-09, "loss": 0.2354, "step": 1221 }, { "epoch": 4.958945767866194, "grad_norm": 0.1631004926441744, "learning_rate": 5.15425407393133e-09, "loss": 0.2494, "step": 1222 }, { "epoch": 4.963000506842372, "grad_norm": 0.16404358947378825, "learning_rate": 3.94626550383137e-09, "loss": 0.257, "step": 1223 }, { "epoch": 4.967055245818551, "grad_norm": 0.17208683942574124, "learning_rate": 2.899322401546112e-09, "loss": 0.2467, "step": 1224 }, { "epoch": 4.971109984794729, "grad_norm": 0.15987660346901905, "learning_rate": 2.013433199010706e-09, "loss": 0.2436, "step": 1225 }, { "epoch": 4.975164723770908, "grad_norm": 0.1669987699481373, "learning_rate": 1.2886050310556563e-09, "loss": 0.257, "step": 1226 }, { "epoch": 4.979219462747086, "grad_norm": 0.17637535835437684, "learning_rate": 7.248437353468695e-10, "loss": 0.2547, "step": 1227 }, { "epoch": 4.983274201723264, "grad_norm": 0.17008220359171167, "learning_rate": 3.221538523412449e-10, "loss": 0.2498, "step": 1228 }, { "epoch": 4.9873289406994425, "grad_norm": 0.1654872200424927, "learning_rate": 8.053862524670663e-11, "loss": 0.2506, "step": 1229 }, { "epoch": 4.991383679675621, "grad_norm": 0.16344337504401157, "learning_rate": 0.0, "loss": 0.2501, "step": 1230 }, { "epoch": 4.991383679675621, "step": 1230, "total_flos": 5.869072169228567e+18, "train_loss": 0.3595038701000252, "train_runtime": 54597.8423, "train_samples_per_second": 2.89, "train_steps_per_second": 0.023 } ], "logging_steps": 1, "max_steps": 1230, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.869072169228567e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }